Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3385 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1047. Min Range: -1.1047

Max Act: 1.1047. Min Act: -0.0000

Data Index: 866321 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 1.1047. Min Range: -1.1047

Max Act: 1.0741. Min Act: -0.0000

Data Index: 305906 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 1.1047. Min Range: -1.1047

Max Act: 1.0198. Min Act: -0.0000

Data Index: 1332528 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.9628. Min Act: -0.0000

Data Index: 418888 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.9599. Min Act: -0.0000

Data Index: 676489 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.9749. Min Act: -0.0000

Data Index: 778332 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.9121. Min Act: -0.0000

Data Index: 230677 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.9644. Min Act: -0.0000

Data Index: 937118 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.9236. Min Act: -0.0000

Data Index: 373981 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.9092. Min Act: -0.0001

Data Index: 138823 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.9384. Min Act: -0.0000

Data Index: 665655 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.9225. Min Act: -0.0000

Data Index: 34557 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.9078. Min Act: -0.0001

Data Index: 91635 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1002549 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.9245. Min Act: -0.0000

Data Index: 584403 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.9103. Min Act: -0.0001

Data Index: 230254 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.8358. Min Act: -0.0000

Data Index: 919396 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1224387 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.8614. Min Act: -0.0000

Data Index: 439325 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 1.1047. Min Range: -1.1047

Max Act: 0.8555. Min Act: -0.0000

Data Index: 546384 (C4 (Web Text))

Max Activating Token Index: 937