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

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

Neuron 1381 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: 0.0240. Min Range: -0.0240

Max Act: 0.0240. Min Act: -0.0006

Data Index: 224620 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0219. Min Act: -0.0006

Data Index: 480210 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0234. Min Act: -0.0006

Data Index: 228951 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0239. Min Act: -0.0006

Data Index: 808024 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0221. Min Act: -0.0006

Data Index: 758279 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0226. Min Act: -0.0006

Data Index: 1125617 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0222. Min Act: -0.0006

Data Index: 140596 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0226. Min Act: -0.0006

Data Index: 475935 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0225. Min Act: -0.0006

Data Index: 489904 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0218. Min Act: -0.0006

Data Index: 830653 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0217. Min Act: -0.0006

Data Index: 853300 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0203. Min Act: -0.0006

Data Index: 331841 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0225. Min Act: -0.0006

Data Index: 165748 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0215. Min Act: -0.0006

Data Index: 907788 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0214. Min Act: -0.0006

Data Index: 562966 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0224. Min Act: -0.0006

Data Index: 1011854 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0214. Min Act: -0.0006

Data Index: 1063563 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0213. Min Act: -0.0006

Data Index: 590238 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0212. Min Act: -0.0006

Data Index: 219385 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0212. Min Act: -0.0006

Data Index: 563544 (C4 (Web Text))

Max Activating Token Index: 37