< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1808 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.6567. Min Act: -0.1700

Data Index: 3991452 (Open Web Text)

Max Activating Token Index: 285

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.6410. Min Act: -0.1700

Data Index: 8511667 (Open Web Text)

Max Activating Token Index: 929

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5868. Min Act: -0.1700

Data Index: 5312442 (Open Web Text)

Max Activating Token Index: 801

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.6190. Min Act: -0.1700

Data Index: 8706658 (Open Web Text)

Max Activating Token Index: 929

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.6071. Min Act: -0.1700

Data Index: 5213142 (Open Web Text)

Max Activating Token Index: 511

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5890. Min Act: -0.1700

Data Index: 3249849 (Open Web Text)

Max Activating Token Index: 224

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5897. Min Act: -0.1700

Data Index: 8499361 (Open Web Text)

Max Activating Token Index: 859

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.6025. Min Act: -0.1700

Data Index: 8283067 (Open Web Text)

Max Activating Token Index: 846

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5647. Min Act: -0.1700

Data Index: 8449634 (Open Web Text)

Max Activating Token Index: 288

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5555. Min Act: -0.1700

Data Index: 4986717 (Open Web Text)

Max Activating Token Index: 95

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5652. Min Act: -0.1700

Data Index: 39669 (Open Web Text)

Max Activating Token Index: 106

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5376. Min Act: -0.1700

Data Index: 7268559 (Open Web Text)

Max Activating Token Index: 173

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5390. Min Act: -0.1700

Data Index: 2083809 (Open Web Text)

Max Activating Token Index: 650

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5376. Min Act: -0.1700

Data Index: 4148598 (Open Web Text)

Max Activating Token Index: 281

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5342. Min Act: -0.1700

Data Index: 7446831 (Open Web Text)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5075. Min Act: -0.1700

Data Index: 3484933 (Open Web Text)

Max Activating Token Index: 704

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5355. Min Act: -0.1700

Data Index: 4177087 (Open Web Text)

Max Activating Token Index: 846

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5122. Min Act: -0.1700

Data Index: 2454637 (Open Web Text)

Max Activating Token Index: 368

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5034. Min Act: -0.1700

Data Index: 5387519 (Open Web Text)

Max Activating Token Index: 998

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.4903. Min Act: -0.1700

Data Index: 83850 (Open Web Text)

Max Activating Token Index: 564

Click toggle to see full text

Truncated

Full Text #19