Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 334 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3897. Min Range: -0.3897

Max Act: 0.3897. Min Act: -0.0000

Data Index: 848720 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 0.3897. Min Range: -0.3897

Max Act: 0.3508. Min Act: -0.0000

Data Index: 727623 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.3897. Min Range: -0.3897

Max Act: 0.3165. Min Act: -0.0000

Data Index: 636638 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 0.3897. Min Range: -0.3897

Max Act: 0.3114. Min Act: -0.0000

Data Index: 484333 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.3897. Min Range: -0.3897

Max Act: 0.2680. Min Act: -0.0000

Data Index: 1155070 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.3897. Min Range: -0.3897

Max Act: 0.2840. Min Act: -0.0000

Data Index: 70654 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 0.3897. Min Range: -0.3897

Max Act: 0.2540. Min Act: -0.0000

Data Index: 1355199 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.3897. Min Range: -0.3897

Max Act: 0.2847. Min Act: -0.0000

Data Index: 161450 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.3897. Min Range: -0.3897

Max Act: 0.2587. Min Act: -0.0000

Data Index: 105900 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.3897. Min Range: -0.3897

Max Act: 0.2679. Min Act: -0.0000

Data Index: 237360 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.3897. Min Range: -0.3897

Max Act: 0.2425. Min Act: -0.0000

Data Index: 324172 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.3897. Min Range: -0.3897

Max Act: 0.2473. Min Act: -0.0000

Data Index: 598003 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 0.3897. Min Range: -0.3897

Max Act: 0.2322. Min Act: -0.0000

Data Index: 911698 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.3897. Min Range: -0.3897

Max Act: 0.2342. Min Act: 0.0000

Data Index: 363832 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.3897. Min Range: -0.3897

Max Act: 0.2188. Min Act: -0.0000

Data Index: 813007 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.3897. Min Range: -0.3897

Max Act: 0.2245. Min Act: -0.0000

Data Index: 943796 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 0.3897. Min Range: -0.3897

Max Act: 0.2298. Min Act: -0.0000

Data Index: 1328721 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.3897. Min Range: -0.3897

Max Act: 0.2433. Min Act: -0.0000

Data Index: 774304 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.3897. Min Range: -0.3897

Max Act: 0.2247. Min Act: -0.0000

Data Index: 1171458 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 0.3897. Min Range: -0.3897

Max Act: 0.2236. Min Act: -0.0000

Data Index: 253762 (C4 (Web Text))

Max Activating Token Index: 779