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

Dataset: Open Web Text

Neuron 1785 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: 3.6373. Min Range: -3.6373

Max Act: 3.6373. Min Act: -0.1700

Data Index: 277309 (Open Web Text)

Max Activating Token Index: 508

Text #1

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.5997. Min Act: -0.1700

Data Index: 2542209 (Open Web Text)

Max Activating Token Index: 509

Text #2

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.6165. Min Act: -0.1700

Data Index: 8263192 (Open Web Text)

Max Activating Token Index: 586

Text #3

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.6040. Min Act: -0.1700

Data Index: 4936012 (Open Web Text)

Max Activating Token Index: 148

Text #4

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.5465. Min Act: -0.1700

Data Index: 6354718 (Open Web Text)

Max Activating Token Index: 754

Text #5

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.5120. Min Act: -0.1700

Data Index: 122255 (Open Web Text)

Max Activating Token Index: 213

Text #6

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.5130. Min Act: -0.1700

Data Index: 1984156 (Open Web Text)

Max Activating Token Index: 280

Text #7

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.5064. Min Act: -0.1700

Data Index: 2158579 (Open Web Text)

Max Activating Token Index: 641

Text #8

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.4863. Min Act: -0.1700

Data Index: 4795329 (Open Web Text)

Max Activating Token Index: 26

Text #9

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.4876. Min Act: -0.1700

Data Index: 7159789 (Open Web Text)

Max Activating Token Index: 134

Text #10

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.4903. Min Act: -0.1700

Data Index: 3531506 (Open Web Text)

Max Activating Token Index: 998

Text #11

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.4942. Min Act: -0.1700

Data Index: 2653962 (Open Web Text)

Max Activating Token Index: 293

Text #12

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.4927. Min Act: -0.1700

Data Index: 4785199 (Open Web Text)

Max Activating Token Index: 481

Text #13

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.4890. Min Act: -0.1700

Data Index: 1235584 (Open Web Text)

Max Activating Token Index: 833

Text #14

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.4285. Min Act: -0.1700

Data Index: 1480984 (Open Web Text)

Max Activating Token Index: 497

Text #15

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.4959. Min Act: -0.1700

Data Index: 1180741 (Open Web Text)

Max Activating Token Index: 768

Text #16

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.4685. Min Act: -0.1700

Data Index: 6370849 (Open Web Text)

Max Activating Token Index: 744

Text #17

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.4715. Min Act: -0.1700

Data Index: 5062554 (Open Web Text)

Max Activating Token Index: 420

Text #18

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.4514. Min Act: -0.1700

Data Index: 6930913 (Open Web Text)

Max Activating Token Index: 367

Text #19

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.4297. Min Act: -0.1700

Data Index: 3278989 (Open Web Text)

Max Activating Token Index: 121