Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 81 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0487. Min Act: -0.0004

Data Index: 921373 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0436. Min Act: -0.0003

Data Index: 434805 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0309. Min Act: -0.0003

Data Index: 852552 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0303. Min Act: -0.0003

Data Index: 49866 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1588644 (Python Code)

Max Activating Token Index: 87

Text #5

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0274. Min Act: -0.0003

Data Index: 990415 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0194. Min Act: -0.0003

Data Index: 1351857 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0221. Min Act: -0.0004

Data Index: 441315 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0240. Min Act: -0.0003

Data Index: 890842 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0166. Min Act: -0.0003

Data Index: 226363 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0196. Min Act: -0.0003

Data Index: 640855 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0214. Min Act: -0.0003

Data Index: 1071943 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0171. Min Act: -0.0003

Data Index: 27454 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0229. Min Act: -0.0003

Data Index: 1149844 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0172. Min Act: -0.0003

Data Index: 1160581 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0213. Min Act: -0.0003

Data Index: 42432 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0190. Min Act: -0.0003

Data Index: 1020874 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0202. Min Act: -0.0003

Data Index: 1002610 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0227. Min Act: -0.0003

Data Index: 838758 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0168. Min Act: -0.0004

Data Index: 759056 (C4 (Web Text))

Max Activating Token Index: 406