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

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

Neuron 1103 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: 0.7025. Min Range: -0.7025

Max Act: 0.7025. Min Act: -0.0000

Data Index: 1325071 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1153056 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.6218. Min Act: -0.0000

Data Index: 236348 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1055739 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5875. Min Act: -0.0000

Data Index: 235344 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5756. Min Act: -0.0000

Data Index: 1113932 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5892. Min Act: -0.0000

Data Index: 101362 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5887. Min Act: -0.0000

Data Index: 1223594 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5660. Min Act: -0.0000

Data Index: 1038202 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5164. Min Act: -0.0000

Data Index: 1183620 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1183135 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5772. Min Act: -0.0000

Data Index: 674141 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5409. Min Act: -0.0000

Data Index: 751182 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5484. Min Act: -0.0000

Data Index: 442063 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5868. Min Act: -0.0000

Data Index: 97889 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5481. Min Act: -0.0000

Data Index: 456735 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5308. Min Act: -0.0000

Data Index: 1128669 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5188. Min Act: -0.0000

Data Index: 1039231 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5142. Min Act: -0.0000

Data Index: 198100 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4974. Min Act: -0.0000

Data Index: 1132876 (C4 (Web Text))

Max Activating Token Index: 913