< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 876 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: 4.3724. Min Range: -4.3724

Max Act: 4.3724. Min Act: -0.1700

Data Index: 5465233 (Open Web Text)

Max Activating Token Index: 224

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 4.3724. Min Range: -4.3724

Max Act: 4.3582. Min Act: -0.1700

Data Index: 3718548 (Open Web Text)

Max Activating Token Index: 1003

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 4.3724. Min Range: -4.3724

Max Act: 4.3715. Min Act: -0.1700

Data Index: 6800973 (Open Web Text)

Max Activating Token Index: 768

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 4.3724. Min Range: -4.3724

Max Act: 4.2852. Min Act: -0.1700

Data Index: 861224 (Open Web Text)

Max Activating Token Index: 257

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 4.3724. Min Range: -4.3724

Max Act: 4.2992. Min Act: -0.1700

Data Index: 8130354 (Open Web Text)

Max Activating Token Index: 606

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 4.3724. Min Range: -4.3724

Max Act: 4.2858. Min Act: -0.1700

Data Index: 8044877 (Open Web Text)

Max Activating Token Index: 846

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 4.3724. Min Range: -4.3724

Max Act: 4.2470. Min Act: -0.1700

Data Index: 2090399 (Open Web Text)

Max Activating Token Index: 228

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 4.3724. Min Range: -4.3724

Max Act: 4.2540. Min Act: -0.1700

Data Index: 4626940 (Open Web Text)

Max Activating Token Index: 330

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 4.3724. Min Range: -4.3724

Max Act: 4.2438. Min Act: -0.1700

Data Index: 8693787 (Open Web Text)

Max Activating Token Index: 908

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 4.3724. Min Range: -4.3724

Max Act: 4.2553. Min Act: -0.1700

Data Index: 4217461 (Open Web Text)

Max Activating Token Index: 802

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 4.3724. Min Range: -4.3724

Max Act: 4.2538. Min Act: -0.1700

Data Index: 2446192 (Open Web Text)

Max Activating Token Index: 166

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 4.3724. Min Range: -4.3724

Max Act: 4.2626. Min Act: -0.1700

Data Index: 5373764 (Open Web Text)

Max Activating Token Index: 470

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 4.3724. Min Range: -4.3724

Max Act: 4.1830. Min Act: -0.1700

Data Index: 3038124 (Open Web Text)

Max Activating Token Index: 689

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 4.3724. Min Range: -4.3724

Max Act: 4.2390. Min Act: -0.1700

Data Index: 1487152 (Open Web Text)

Max Activating Token Index: 425

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 4.3724. Min Range: -4.3724

Max Act: 4.2134. Min Act: -0.1700

Data Index: 7705210 (Open Web Text)

Max Activating Token Index: 812

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 4.3724. Min Range: -4.3724

Max Act: 4.1841. Min Act: -0.1700

Data Index: 347933 (Open Web Text)

Max Activating Token Index: 612

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 4.3724. Min Range: -4.3724

Max Act: 4.1957. Min Act: -0.1700

Data Index: 5483542 (Open Web Text)

Max Activating Token Index: 123

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 4.3724. Min Range: -4.3724

Max Act: 4.1900. Min Act: -0.1700

Data Index: 6344716 (Open Web Text)

Max Activating Token Index: 403

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 4.3724. Min Range: -4.3724

Max Act: 4.1864. Min Act: -0.1700

Data Index: 4823793 (Open Web Text)

Max Activating Token Index: 718

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 4.3724. Min Range: -4.3724

Max Act: 4.1529. Min Act: -0.1700

Data Index: 4909067 (Open Web Text)

Max Activating Token Index: 404

Click toggle to see full text

Truncated

Full Text #19