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

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

Neuron 5035 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1158. Min Range: -1.1158

Max Act: 1.1158. Min Act: -0.0000

Data Index: 761703 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.9866. Min Act: 0.0000

Data Index: 20911 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.8951. Min Act: -0.0000

Data Index: 1347632 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.8352. Min Act: -0.0000

Data Index: 1270680 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.8452. Min Act: -0.0000

Data Index: 374426 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.8043. Min Act: -0.0000

Data Index: 1208431 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1158087 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.6446. Min Act: 0.0000

Data Index: 172418 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1259533 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.6189. Min Act: 0.0002

Data Index: 158585 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.6052. Min Act: -0.0000

Data Index: 1196765 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.5791. Min Act: -0.0000

Data Index: 78012 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.5804. Min Act: -0.0000

Data Index: 908882 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.5955. Min Act: 0.0000

Data Index: 1410997 (Python Code)

Max Activating Token Index: 422

Text #14

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1038090 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.5327. Min Act: -0.0000

Data Index: 736198 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.5095. Min Act: -0.0000

Data Index: 1024662 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.5175. Min Act: -0.0000

Data Index: 773604 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.5019. Min Act: -0.0000

Data Index: 1452213 (Python Code)

Max Activating Token Index: 167

Text #19

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.5209. Min Act: -0.0000

Data Index: 914047 (C4 (Web Text))

Max Activating Token Index: 414