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

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

Neuron 4056 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.4363. Min Act: -0.0000

Data Index: 738193 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.4128. Min Act: -0.0000

Data Index: 687963 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3896. Min Act: -0.0000

Data Index: 432258 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.4055. Min Act: -0.0000

Data Index: 141946 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3559. Min Act: -0.0000

Data Index: 640034 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3694. Min Act: -0.0000

Data Index: 303806 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3503. Min Act: -0.0000

Data Index: 382996 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3446. Min Act: -0.0000

Data Index: 1319397 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3423. Min Act: -0.0000

Data Index: 431942 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3439. Min Act: -0.0000

Data Index: 1305502 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3132. Min Act: -0.0000

Data Index: 503117 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3092. Min Act: -0.0000

Data Index: 732447 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3184. Min Act: -0.0000

Data Index: 103701 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3310. Min Act: -0.0000

Data Index: 961664 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3091. Min Act: -0.0000

Data Index: 822050 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3149. Min Act: -0.0000

Data Index: 437703 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3142. Min Act: -0.0000

Data Index: 169692 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3130. Min Act: -0.0000

Data Index: 806816 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3030. Min Act: -0.0000

Data Index: 288187 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.2716. Min Act: -0.0000

Data Index: 1127318 (C4 (Web Text))

Max Activating Token Index: 825