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

Dataset: Open Web Text

Neuron 245 in Layer 3

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: 4.1334. Min Range: -4.1334

Max Act: 4.0896. Min Act: -0.1700

Data Index: 2607417 (Open Web Text)

Max Activating Token Index: 490

Text #1

Max Range: 4.1334. Min Range: -4.1334

Max Act: 4.1334. Min Act: -0.1700

Data Index: 7206799 (Open Web Text)

Max Activating Token Index: 117

Text #2

Max Range: 4.1334. Min Range: -4.1334

Max Act: 4.0756. Min Act: -0.1700

Data Index: 7161471 (Open Web Text)

Max Activating Token Index: 24

Text #3

Max Range: 4.1334. Min Range: -4.1334

Max Act: 4.0905. Min Act: -0.1700

Data Index: 212067 (Open Web Text)

Max Activating Token Index: 166

Text #4

Max Range: 4.1334. Min Range: -4.1334

Max Act: 4.0303. Min Act: -0.1700

Data Index: 1231587 (Open Web Text)

Max Activating Token Index: 370

Text #5

Max Range: 4.1334. Min Range: -4.1334

Max Act: 4.0600. Min Act: -0.1700

Data Index: 3107318 (Open Web Text)

Max Activating Token Index: 449

Text #6

Max Range: 4.1334. Min Range: -4.1334

Max Act: 4.0447. Min Act: -0.1700

Data Index: 1653870 (Open Web Text)

Max Activating Token Index: 72

Text #7

Max Range: 4.1334. Min Range: -4.1334

Max Act: 4.0601. Min Act: -0.1700

Data Index: 5273600 (Open Web Text)

Max Activating Token Index: 473

Text #8

Max Range: 4.1334. Min Range: -4.1334

Max Act: 4.0371. Min Act: -0.1700

Data Index: 6043592 (Open Web Text)

Max Activating Token Index: 91

Text #9

Max Range: 4.1334. Min Range: -4.1334

Max Act: 4.0617. Min Act: -0.1700

Data Index: 3678145 (Open Web Text)

Max Activating Token Index: 274

Text #10

Max Range: 4.1334. Min Range: -4.1334

Max Act: 4.0162. Min Act: -0.1700

Data Index: 1212390 (Open Web Text)

Max Activating Token Index: 931

Text #11

Max Range: 4.1334. Min Range: -4.1334

Max Act: 4.0236. Min Act: -0.1700

Data Index: 1212391 (Open Web Text)

Max Activating Token Index: 391

Text #12

Max Range: 4.1334. Min Range: -4.1334

Max Act: 4.0136. Min Act: -0.1700

Data Index: 8178142 (Open Web Text)

Max Activating Token Index: 111

Text #13

Max Range: 4.1334. Min Range: -4.1334

Max Act: 4.0381. Min Act: -0.1700

Data Index: 1069731 (Open Web Text)

Max Activating Token Index: 609

Text #14

Max Range: 4.1334. Min Range: -4.1334

Max Act: 4.0062. Min Act: -0.1700

Data Index: 7852730 (Open Web Text)

Max Activating Token Index: 955

Text #15

Max Range: 4.1334. Min Range: -4.1334

Max Act: 4.0097. Min Act: -0.1700

Data Index: 5632853 (Open Web Text)

Max Activating Token Index: 565

Text #16

Max Range: 4.1334. Min Range: -4.1334

Max Act: 4.0100. Min Act: -0.1700

Data Index: 4037531 (Open Web Text)

Max Activating Token Index: 112

Text #17

Max Range: 4.1334. Min Range: -4.1334

Max Act: 4.0010. Min Act: -0.1700

Data Index: 5776279 (Open Web Text)

Max Activating Token Index: 764

Text #18

Max Range: 4.1334. Min Range: -4.1334

Max Act: 3.9743. Min Act: -0.1700

Data Index: 5346085 (Open Web Text)

Max Activating Token Index: 246

Text #19

Max Range: 4.1334. Min Range: -4.1334

Max Act: 3.9842. Min Act: -0.1700

Data Index: 5256284 (Open Web Text)

Max Activating Token Index: 372