Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 642 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.8898. Min Act: -0.0000

Data Index: 957010 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.9177. Min Act: -0.0000

Data Index: 675182 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.7842. Min Act: -0.0000

Data Index: 704476 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.7785. Min Act: -0.0000

Data Index: 109694 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.6698. Min Act: -0.0000

Data Index: 662415 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.7649. Min Act: -0.0000

Data Index: 158189 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.7434. Min Act: -0.0000

Data Index: 1230816 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.7361. Min Act: -0.0000

Data Index: 1323549 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.6370. Min Act: -0.0000

Data Index: 1187955 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.6205. Min Act: -0.0000

Data Index: 256337 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.6897. Min Act: -0.0000

Data Index: 1191362 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.6580. Min Act: -0.0000

Data Index: 307552 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.6507. Min Act: -0.0000

Data Index: 1359445 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.7561. Min Act: -0.0000

Data Index: 683499 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.7455. Min Act: -0.0000

Data Index: 296075 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.6554. Min Act: -0.0000

Data Index: 152010 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.6358. Min Act: -0.0000

Data Index: 1284049 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.6143. Min Act: -0.0000

Data Index: 373241 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.6023. Min Act: -0.0000

Data Index: 805168 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 1.9177. Min Range: -1.9177

Max Act: 1.6085. Min Act: -0.0000

Data Index: 1140784 (C4 (Web Text))

Max Activating Token Index: 327