< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 42 in Layer 39

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')



Text #0

Max Range: 10.8225. Min Range: -10.8225

Max Act: 10.8225. Min Act: -0.1700

Data Index: 1022955 (Open Web Text)

Max Activating Token Index: 587

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.8225. Min Range: -10.8225

Max Act: 10.8225. Min Act: -0.1700

Data Index: 4281972 (Open Web Text)

Max Activating Token Index: 170

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.8225. Min Range: -10.8225

Max Act: 10.4475. Min Act: -0.1700

Data Index: 4843618 (Open Web Text)

Max Activating Token Index: 832

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.8225. Min Range: -10.8225

Max Act: 10.4475. Min Act: -0.1700

Data Index: 676799 (Open Web Text)

Max Activating Token Index: 592

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.8225. Min Range: -10.8225

Max Act: 10.4475. Min Act: -0.1700

Data Index: 3547200 (Open Web Text)

Max Activating Token Index: 73

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.8225. Min Range: -10.8225

Max Act: 10.4475. Min Act: -0.1700

Data Index: 6860519 (Open Web Text)

Max Activating Token Index: 369

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.8225. Min Range: -10.8225

Max Act: 10.3225. Min Act: -0.1700

Data Index: 5439316 (Open Web Text)

Max Activating Token Index: 241

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.8225. Min Range: -10.8225

Max Act: 10.3225. Min Act: -0.1700

Data Index: 6322497 (Open Web Text)

Max Activating Token Index: 344

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.8225. Min Range: -10.8225

Max Act: 10.1975. Min Act: -0.1700

Data Index: 6970215 (Open Web Text)

Max Activating Token Index: 219

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.8225. Min Range: -10.8225

Max Act: 10.1975. Min Act: -0.1700

Data Index: 2475809 (Open Web Text)

Max Activating Token Index: 694

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.8225. Min Range: -10.8225

Max Act: 10.0725. Min Act: -0.1700

Data Index: 803990 (Open Web Text)

Max Activating Token Index: 165

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.8225. Min Range: -10.8225

Max Act: 10.1350. Min Act: -0.1700

Data Index: 2979492 (Open Web Text)

Max Activating Token Index: 123

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.8225. Min Range: -10.8225

Max Act: 10.1350. Min Act: -0.1700

Data Index: 4537507 (Open Web Text)

Max Activating Token Index: 525

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.8225. Min Range: -10.8225

Max Act: 10.0100. Min Act: -0.1700

Data Index: 5090850 (Open Web Text)

Max Activating Token Index: 493

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.8225. Min Range: -10.8225

Max Act: 10.0100. Min Act: -0.1700

Data Index: 3574216 (Open Web Text)

Max Activating Token Index: 1008

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.8225. Min Range: -10.8225

Max Act: 10.0725. Min Act: -0.1700

Data Index: 803994 (Open Web Text)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.8225. Min Range: -10.8225

Max Act: 10.0725. Min Act: -0.1700

Data Index: 3118837 (Open Web Text)

Max Activating Token Index: 535

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.8225. Min Range: -10.8225

Max Act: 10.0725. Min Act: -0.1700

Data Index: 1207530 (Open Web Text)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.8225. Min Range: -10.8225

Max Act: 10.0100. Min Act: -0.1700

Data Index: 790740 (Open Web Text)

Max Activating Token Index: 343

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.8225. Min Range: -10.8225

Max Act: 10.0100. Min Act: -0.1700

Data Index: 3228982 (Open Web Text)

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #19