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

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

Neuron 3285 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: 1.0235. Min Range: -1.0235

Max Act: 1.0235. Min Act: -0.0000

Data Index: 996230 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.9401. Min Act: -0.0000

Data Index: 401964 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.9531. Min Act: -0.0000

Data Index: 200878 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.8015. Min Act: -0.0000

Data Index: 801578 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.8039. Min Act: -0.0000

Data Index: 712964 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.7554. Min Act: 0.0001

Data Index: 1308543 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.7078. Min Act: -0.0000

Data Index: 1036846 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.6788. Min Act: -0.0000

Data Index: 1033882 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.7055. Min Act: -0.0000

Data Index: 607927 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.6531. Min Act: -0.0000

Data Index: 1150425 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.6489. Min Act: -0.0000

Data Index: 1320326 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.6516. Min Act: -0.0000

Data Index: 853765 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.6031. Min Act: -0.0000

Data Index: 530089 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.6062. Min Act: -0.0000

Data Index: 879023 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.6214. Min Act: -0.0000

Data Index: 579532 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.5797. Min Act: -0.0000

Data Index: 628477 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.6086. Min Act: -0.0000

Data Index: 274289 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.6070. Min Act: -0.0000

Data Index: 624868 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.5848. Min Act: -0.0000

Data Index: 712422 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.5781. Min Act: -0.0000

Data Index: 470327 (C4 (Web Text))

Max Activating Token Index: 1003