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

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

Neuron 37 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: 0.0277. Min Range: -0.0277

Max Act: 0.0277. Min Act: -0.0006

Data Index: 554313 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0260. Min Act: -0.0006

Data Index: 245821 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0263. Min Act: -0.0006

Data Index: 955838 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0256. Min Act: -0.0006

Data Index: 1088810 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0255. Min Act: -0.0006

Data Index: 927070 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0246. Min Act: -0.0006

Data Index: 989763 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0246. Min Act: -0.0006

Data Index: 892858 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0228. Min Act: -0.0006

Data Index: 960405 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0226. Min Act: -0.0006

Data Index: 138925 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0219. Min Act: -0.0006

Data Index: 405732 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0233. Min Act: -0.0006

Data Index: 375423 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0218. Min Act: -0.0006

Data Index: 133400 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0216. Min Act: -0.0006

Data Index: 1358639 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0219. Min Act: -0.0006

Data Index: 422171 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0217. Min Act: -0.0006

Data Index: 300734 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0215. Min Act: -0.0006

Data Index: 201656 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0210. Min Act: -0.0006

Data Index: 1223225 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0214. Min Act: -0.0006

Data Index: 142815 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0223. Min Act: -0.0006

Data Index: 1198012 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0218. Min Act: -0.0006

Data Index: 1217823 (C4 (Web Text))

Max Activating Token Index: 884