< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 41 in Layer 23

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.4977. Min Act: -0.1700

Data Index: 2649991 (Open Web Text)

Max Activating Token Index: 476

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.4664. Min Act: -0.1700

Data Index: 6538121 (Open Web Text)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.4039. Min Act: -0.1700

Data Index: 5102466 (Open Web Text)

Max Activating Token Index: 319

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.3727. Min Act: -0.1700

Data Index: 92315 (Open Web Text)

Max Activating Token Index: 751

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.2789. Min Act: -0.1700

Data Index: 7977098 (Open Web Text)

Max Activating Token Index: 388

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.2789. Min Act: -0.1700

Data Index: 6554945 (Open Web Text)

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.2476. Min Act: -0.1700

Data Index: 8109275 (Open Web Text)

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.2164. Min Act: -0.1700

Data Index: 6109944 (Open Web Text)

Max Activating Token Index: 787

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.2476. Min Act: -0.1700

Data Index: 4091733 (Open Web Text)

Max Activating Token Index: 600

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.2476. Min Act: -0.1700

Data Index: 8392717 (Open Web Text)

Max Activating Token Index: 861

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.2476. Min Act: -0.1700

Data Index: 234601 (Open Web Text)

Max Activating Token Index: 694

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.2476. Min Act: -0.1700

Data Index: 4865597 (Open Web Text)

Max Activating Token Index: 718

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.2476. Min Act: -0.1700

Data Index: 758977 (Open Web Text)

Max Activating Token Index: 424

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.2476. Min Act: -0.1700

Data Index: 5052315 (Open Web Text)

Max Activating Token Index: 453

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.2476. Min Act: -0.1700

Data Index: 1961712 (Open Web Text)

Max Activating Token Index: 568

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.2164. Min Act: -0.1700

Data Index: 3418193 (Open Web Text)

Max Activating Token Index: 895

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.1851. Min Act: -0.1700

Data Index: 2225747 (Open Web Text)

Max Activating Token Index: 196

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.2164. Min Act: -0.1700

Data Index: 4097172 (Open Web Text)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.1851. Min Act: -0.1700

Data Index: 5660735 (Open Web Text)

Max Activating Token Index: 490

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.1851. Min Act: -0.1700

Data Index: 2092169 (Open Web Text)

Max Activating Token Index: 446

Click toggle to see full text

Truncated

Full Text #19