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

Dataset: Open Web Text

Neuron 2094 in Layer 6

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: 4.0943. Min Range: -4.0943

Max Act: 4.0943. Min Act: -0.1700

Data Index: 6383861 (Open Web Text)

Max Activating Token Index: 922

Text #1

Max Range: 4.0943. Min Range: -4.0943

Max Act: 4.0280. Min Act: -0.1700

Data Index: 3031848 (Open Web Text)

Max Activating Token Index: 670

Text #2

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.9727. Min Act: -0.1700

Data Index: 6628705 (Open Web Text)

Max Activating Token Index: 294

Text #3

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.9429. Min Act: -0.1700

Data Index: 4356819 (Open Web Text)

Max Activating Token Index: 346

Text #4

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.9638. Min Act: -0.1700

Data Index: 6191326 (Open Web Text)

Max Activating Token Index: 150

Text #5

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.9153. Min Act: -0.1700

Data Index: 8362535 (Open Web Text)

Max Activating Token Index: 371

Text #6

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.9262. Min Act: -0.1700

Data Index: 7825772 (Open Web Text)

Max Activating Token Index: 393

Text #7

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.9391. Min Act: -0.1700

Data Index: 2386765 (Open Web Text)

Max Activating Token Index: 513

Text #8

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.8682. Min Act: -0.1700

Data Index: 3286497 (Open Web Text)

Max Activating Token Index: 962

Text #9

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.8916. Min Act: -0.1700

Data Index: 394137 (Open Web Text)

Max Activating Token Index: 833

Text #10

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.8693. Min Act: -0.1700

Data Index: 3550886 (Open Web Text)

Max Activating Token Index: 387

Text #11

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.8687. Min Act: -0.1700

Data Index: 1800063 (Open Web Text)

Max Activating Token Index: 761

Text #12

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.8687. Min Act: -0.1700

Data Index: 4843025 (Open Web Text)

Max Activating Token Index: 963

Text #13

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.8623. Min Act: -0.1700

Data Index: 7698609 (Open Web Text)

Max Activating Token Index: 672

Text #14

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.8757. Min Act: -0.1700

Data Index: 7634814 (Open Web Text)

Max Activating Token Index: 926

Text #15

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.8302. Min Act: -0.1700

Data Index: 1693832 (Open Web Text)

Max Activating Token Index: 61

Text #16

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.8346. Min Act: -0.1700

Data Index: 1637226 (Open Web Text)

Max Activating Token Index: 479

Text #17

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.8872. Min Act: -0.1700

Data Index: 910113 (Open Web Text)

Max Activating Token Index: 817

Text #18

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.8556. Min Act: -0.1700

Data Index: 863900 (Open Web Text)

Max Activating Token Index: 286

Text #19

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.8252. Min Act: -0.1700

Data Index: 2832198 (Open Web Text)

Max Activating Token Index: 480