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

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

Neuron 4450 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.6177. Min Act: -0.0000

Data Index: 506320 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.5860. Min Act: -0.0000

Data Index: 317693 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.5187. Min Act: -0.0000

Data Index: 1267466 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.4422. Min Act: -0.0000

Data Index: 982358 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.4131. Min Act: -0.0000

Data Index: 239621 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.4079. Min Act: -0.0000

Data Index: 665154 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.4166. Min Act: -0.0000

Data Index: 2587 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1345131 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.4006. Min Act: -0.0000

Data Index: 1222980 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.4175. Min Act: -0.0000

Data Index: 1305086 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.4013. Min Act: -0.0000

Data Index: 890030 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.4040. Min Act: -0.0000

Data Index: 817393 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.3698. Min Act: -0.0000

Data Index: 959852 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.3488. Min Act: 0.0000

Data Index: 937930 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.3472. Min Act: -0.0000

Data Index: 352607 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.3319. Min Act: -0.0000

Data Index: 349782 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.3370. Min Act: -0.0000

Data Index: 467587 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.3513. Min Act: -0.0000

Data Index: 742450 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.3358. Min Act: -0.0000

Data Index: 325748 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.3281. Min Act: -0.0000

Data Index: 197000 (C4 (Web Text))

Max Activating Token Index: 566