Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1839 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0238. Min Act: -0.0006

Data Index: 680476 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0210. Min Act: -0.0006

Data Index: 462681 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0184. Min Act: -0.0006

Data Index: 1264982 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0192. Min Act: -0.0006

Data Index: 881598 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0179. Min Act: -0.0006

Data Index: 1063936 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0183. Min Act: -0.0006

Data Index: 826928 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0186. Min Act: -0.0006

Data Index: 438658 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0180. Min Act: -0.0006

Data Index: 1159246 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0176. Min Act: -0.0006

Data Index: 373514 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0179. Min Act: -0.0006

Data Index: 1290836 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0178. Min Act: -0.0006

Data Index: 541616 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0175. Min Act: -0.0006

Data Index: 990691 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0174. Min Act: -0.0006

Data Index: 1100276 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0172. Min Act: -0.0006

Data Index: 905658 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0171. Min Act: -0.0006

Data Index: 15204 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0170. Min Act: -0.0006

Data Index: 408098 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0169. Min Act: -0.0006

Data Index: 293020 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0168. Min Act: -0.0006

Data Index: 348529 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0168. Min Act: -0.0006

Data Index: 1117001 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0168. Min Act: -0.0006

Data Index: 916212 (C4 (Web Text))

Max Activating Token Index: 39