Model: GELU Model: 2 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 363 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.5235. Min Range: -3.5235

Max Act: 3.5235. Min Act: -0.1700

Data Index: 21674 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 3.5235. Min Range: -3.5235

Max Act: 3.4608. Min Act: -0.1700

Data Index: 675160 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 3.5235. Min Range: -3.5235

Max Act: 3.3981. Min Act: -0.1700

Data Index: 1520707 (Python Code)

Max Activating Token Index: 636

Text #3

Max Range: 3.5235. Min Range: -3.5235

Max Act: 3.3667. Min Act: -0.1700

Data Index: 1205074 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 3.5235. Min Range: -3.5235

Max Act: 3.3510. Min Act: -0.1700

Data Index: 1260403 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 3.5235. Min Range: -3.5235

Max Act: 3.3981. Min Act: -0.1700

Data Index: 875647 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 3.5235. Min Range: -3.5235

Max Act: 3.3981. Min Act: -0.1700

Data Index: 1494131 (Python Code)

Max Activating Token Index: 370

Text #7

Max Range: 3.5235. Min Range: -3.5235

Max Act: 3.3353. Min Act: -0.1700

Data Index: 163695 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 3.5235. Min Range: -3.5235

Max Act: 3.2096. Min Act: -0.1700

Data Index: 544231 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 3.5235. Min Range: -3.5235

Max Act: 3.3353. Min Act: -0.1700

Data Index: 1279426 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 3.5235. Min Range: -3.5235

Max Act: 3.3039. Min Act: -0.1700

Data Index: 783581 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 3.5235. Min Range: -3.5235

Max Act: 3.3353. Min Act: -0.1700

Data Index: 1577699 (Python Code)

Max Activating Token Index: 145

Text #12

Max Range: 3.5235. Min Range: -3.5235

Max Act: 3.2725. Min Act: -0.1700

Data Index: 783445 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 3.5235. Min Range: -3.5235

Max Act: 3.2253. Min Act: -0.1700

Data Index: 309532 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 3.5235. Min Range: -3.5235

Max Act: 3.3196. Min Act: -0.1700

Data Index: 123268 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 3.5235. Min Range: -3.5235

Max Act: 3.3353. Min Act: -0.1700

Data Index: 937450 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 3.5235. Min Range: -3.5235

Max Act: 3.3667. Min Act: -0.1700

Data Index: 20747 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 3.5235. Min Range: -3.5235

Max Act: 3.3196. Min Act: -0.1700

Data Index: 1012928 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 3.5235. Min Range: -3.5235

Max Act: 3.3196. Min Act: -0.1700

Data Index: 168894 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 3.5235. Min Range: -3.5235

Max Act: 3.2568. Min Act: -0.1700

Data Index: 240176 (C4 (Web Text))

Max Activating Token Index: 271