Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1928 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0006

Data Index: 132702 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0246. Min Act: -0.0006

Data Index: 824959 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0235. Min Act: -0.0006

Data Index: 70119 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0221. Min Act: -0.0006

Data Index: 112143 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0215. Min Act: -0.0006

Data Index: 1079678 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0213. Min Act: -0.0006

Data Index: 118481 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0214. Min Act: -0.0006

Data Index: 1238080 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0209. Min Act: -0.0006

Data Index: 371791 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0203. Min Act: -0.0006

Data Index: 68094 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0208. Min Act: -0.0006

Data Index: 1078255 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0185. Min Act: -0.0006

Data Index: 1472616 (Python Code)

Max Activating Token Index: 736

Text #11

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0184. Min Act: -0.0006

Data Index: 669647 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0184. Min Act: -0.0006

Data Index: 12921 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0186. Min Act: -0.0006

Data Index: 438963 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0179. Min Act: -0.0006

Data Index: 715407 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1288271 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0181. Min Act: -0.0006

Data Index: 946566 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0177. Min Act: -0.0006

Data Index: 229391 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0176. Min Act: -0.0006

Data Index: 538812 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0176. Min Act: -0.0006

Data Index: 110048 (C4 (Web Text))

Max Activating Token Index: 114