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

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

Neuron 354 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0973. Min Range: -1.0973

Max Act: 1.0973. Min Act: -0.0000

Data Index: 44746 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.8882. Min Act: -0.0000

Data Index: 310657 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.8276. Min Act: -0.0000

Data Index: 446047 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.7701. Min Act: -0.0000

Data Index: 136858 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.8047. Min Act: -0.0000

Data Index: 635357 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.8004. Min Act: -0.0000

Data Index: 1077635 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.8025. Min Act: -0.0000

Data Index: 287858 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.7027. Min Act: -0.0000

Data Index: 394895 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.7514. Min Act: -0.0000

Data Index: 311284 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.7247. Min Act: -0.0000

Data Index: 372138 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.6920. Min Act: -0.0000

Data Index: 1280319 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.7081. Min Act: -0.0000

Data Index: 334014 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.7242. Min Act: -0.0000

Data Index: 537298 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.7038. Min Act: -0.0000

Data Index: 1157252 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.6867. Min Act: -0.0000

Data Index: 693749 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.7036. Min Act: -0.0000

Data Index: 214656 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.7016. Min Act: -0.0000

Data Index: 750935 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.7241. Min Act: -0.0000

Data Index: 455125 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.6705. Min Act: -0.0000

Data Index: 792643 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.6429. Min Act: -0.0000

Data Index: 352172 (C4 (Web Text))

Max Activating Token Index: 1018