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

Dataset: Open Web Text

Neuron 1171 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 4.3233. Min Range: -4.3233

Max Act: 4.3233. Min Act: -0.1700

Data Index: 8750419 (Open Web Text)

Max Activating Token Index: 1014

Text #1

Max Range: 4.3233. Min Range: -4.3233

Max Act: 4.2326. Min Act: -0.1700

Data Index: 2888633 (Open Web Text)

Max Activating Token Index: 664

Text #2

Max Range: 4.3233. Min Range: -4.3233

Max Act: 4.1534. Min Act: -0.1700

Data Index: 6621090 (Open Web Text)

Max Activating Token Index: 672

Text #3

Max Range: 4.3233. Min Range: -4.3233

Max Act: 4.1335. Min Act: -0.1700

Data Index: 4783625 (Open Web Text)

Max Activating Token Index: 173

Text #4

Max Range: 4.3233. Min Range: -4.3233

Max Act: 4.1384. Min Act: -0.1700

Data Index: 3731955 (Open Web Text)

Max Activating Token Index: 948

Text #5

Max Range: 4.3233. Min Range: -4.3233

Max Act: 4.1055. Min Act: -0.1700

Data Index: 5096914 (Open Web Text)

Max Activating Token Index: 280

Text #6

Max Range: 4.3233. Min Range: -4.3233

Max Act: 4.1036. Min Act: -0.1700

Data Index: 6720093 (Open Web Text)

Max Activating Token Index: 714

Text #7

Max Range: 4.3233. Min Range: -4.3233

Max Act: 4.0947. Min Act: -0.1700

Data Index: 6726102 (Open Web Text)

Max Activating Token Index: 645

Text #8

Max Range: 4.3233. Min Range: -4.3233

Max Act: 4.0762. Min Act: -0.1700

Data Index: 2869079 (Open Web Text)

Max Activating Token Index: 875

Text #9

Max Range: 4.3233. Min Range: -4.3233

Max Act: 4.0706. Min Act: -0.1700

Data Index: 472573 (Open Web Text)

Max Activating Token Index: 558

Text #10

Max Range: 4.3233. Min Range: -4.3233

Max Act: 4.0932. Min Act: -0.1700

Data Index: 4588927 (Open Web Text)

Max Activating Token Index: 801

Text #11

Max Range: 4.3233. Min Range: -4.3233

Max Act: 4.0651. Min Act: -0.1700

Data Index: 8015327 (Open Web Text)

Max Activating Token Index: 219

Text #12

Max Range: 4.3233. Min Range: -4.3233

Max Act: 4.1012. Min Act: -0.1700

Data Index: 4571489 (Open Web Text)

Max Activating Token Index: 416

Text #13

Max Range: 4.3233. Min Range: -4.3233

Max Act: 4.0470. Min Act: -0.1700

Data Index: 1075637 (Open Web Text)

Max Activating Token Index: 735

Text #14

Max Range: 4.3233. Min Range: -4.3233

Max Act: 4.0588. Min Act: -0.1700

Data Index: 4264138 (Open Web Text)

Max Activating Token Index: 144

Text #15

Max Range: 4.3233. Min Range: -4.3233

Max Act: 4.0872. Min Act: -0.1700

Data Index: 2383934 (Open Web Text)

Max Activating Token Index: 951

Text #16

Max Range: 4.3233. Min Range: -4.3233

Max Act: 4.0812. Min Act: -0.1700

Data Index: 8021791 (Open Web Text)

Max Activating Token Index: 524

Text #17

Max Range: 4.3233. Min Range: -4.3233

Max Act: 4.0410. Min Act: -0.1700

Data Index: 750233 (Open Web Text)

Max Activating Token Index: 76

Text #18

Max Range: 4.3233. Min Range: -4.3233

Max Act: 4.0549. Min Act: -0.1700

Data Index: 6092154 (Open Web Text)

Max Activating Token Index: 293

Text #19

Max Range: 4.3233. Min Range: -4.3233

Max Act: 4.0342. Min Act: -0.1700

Data Index: 4060343 (Open Web Text)

Max Activating Token Index: 812