< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 6331 in Layer 47

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 10.4862. Min Range: -10.4862

Max Act: 10.4862. Min Act: -0.1700

Data Index: 5557702 (Open Web Text)

Max Activating Token Index: 427

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.4862. Min Range: -10.4862

Max Act: 10.3612. Min Act: -0.1700

Data Index: 391568 (Open Web Text)

Max Activating Token Index: 758

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.4862. Min Range: -10.4862

Max Act: 10.2987. Min Act: -0.1700

Data Index: 8509693 (Open Web Text)

Max Activating Token Index: 187

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.4862. Min Range: -10.4862

Max Act: 10.1737. Min Act: -0.1700

Data Index: 5127375 (Open Web Text)

Max Activating Token Index: 434

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.4862. Min Range: -10.4862

Max Act: 10.1737. Min Act: -0.1700

Data Index: 5186631 (Open Web Text)

Max Activating Token Index: 113

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.4862. Min Range: -10.4862

Max Act: 9.8612. Min Act: -0.1700

Data Index: 118162 (Open Web Text)

Max Activating Token Index: 648

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.4862. Min Range: -10.4862

Max Act: 9.8612. Min Act: -0.1700

Data Index: 2389413 (Open Web Text)

Max Activating Token Index: 290

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.4862. Min Range: -10.4862

Max Act: 9.7987. Min Act: -0.1700

Data Index: 1200778 (Open Web Text)

Max Activating Token Index: 63

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.4862. Min Range: -10.4862

Max Act: 9.8612. Min Act: -0.1700

Data Index: 189169 (Open Web Text)

Max Activating Token Index: 778

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.4862. Min Range: -10.4862

Max Act: 9.7362. Min Act: -0.1700

Data Index: 2197718 (Open Web Text)

Max Activating Token Index: 763

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.4862. Min Range: -10.4862

Max Act: 9.6737. Min Act: -0.1700

Data Index: 1859080 (Open Web Text)

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.4862. Min Range: -10.4862

Max Act: 9.7362. Min Act: -0.1700

Data Index: 8255928 (Open Web Text)

Max Activating Token Index: 240

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.4862. Min Range: -10.4862

Max Act: 9.7362. Min Act: -0.1700

Data Index: 5498127 (Open Web Text)

Max Activating Token Index: 234

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.4862. Min Range: -10.4862

Max Act: 9.6737. Min Act: -0.1700

Data Index: 3543048 (Open Web Text)

Max Activating Token Index: 260

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.4862. Min Range: -10.4862

Max Act: 9.6112. Min Act: -0.1700

Data Index: 5220232 (Open Web Text)

Max Activating Token Index: 659

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.4862. Min Range: -10.4862

Max Act: 9.6112. Min Act: -0.1700

Data Index: 2963088 (Open Web Text)

Max Activating Token Index: 438

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.4862. Min Range: -10.4862

Max Act: 9.6112. Min Act: -0.1700

Data Index: 6968331 (Open Web Text)

Max Activating Token Index: 736

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.4862. Min Range: -10.4862

Max Act: 9.5487. Min Act: -0.1700

Data Index: 8694879 (Open Web Text)

Max Activating Token Index: 666

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.4862. Min Range: -10.4862

Max Act: 9.5487. Min Act: -0.1700

Data Index: 6868998 (Open Web Text)

Max Activating Token Index: 497

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.4862. Min Range: -10.4862

Max Act: 9.4862. Min Act: -0.1699

Data Index: 2658717 (Open Web Text)

Max Activating Token Index: 801

Click toggle to see full text

Truncated

Full Text #19