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

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

Neuron 434 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0255. Min Act: -0.0003

Data Index: 1001181 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0218. Min Act: -0.0003

Data Index: 166203 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0211. Min Act: -0.0004

Data Index: 1141854 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0194. Min Act: -0.0004

Data Index: 870821 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0193. Min Act: -0.0003

Data Index: 403470 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0196. Min Act: -0.0003

Data Index: 88663 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0196. Min Act: -0.0003

Data Index: 980371 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0196. Min Act: -0.0003

Data Index: 593110 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0202. Min Act: -0.0003

Data Index: 802484 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0186. Min Act: -0.0003

Data Index: 777776 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0196. Min Act: -0.0003

Data Index: 1141589 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0190. Min Act: -0.0003

Data Index: 142323 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0188. Min Act: -0.0003

Data Index: 839353 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0199. Min Act: -0.0003

Data Index: 460507 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0191. Min Act: -0.0003

Data Index: 825069 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0188. Min Act: -0.0003

Data Index: 1296975 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0183. Min Act: -0.0003

Data Index: 136051 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0185. Min Act: -0.0003

Data Index: 879372 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0177. Min Act: -0.0003

Data Index: 128080 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0180. Min Act: -0.0003

Data Index: 564107 (C4 (Web Text))

Max Activating Token Index: 471