Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1190 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0286. Min Act: -0.0003

Data Index: 516394 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0209. Min Act: -0.0003

Data Index: 1076513 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0206. Min Act: -0.0003

Data Index: 989491 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0203. Min Act: -0.0003

Data Index: 63918 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0199. Min Act: -0.0003

Data Index: 413590 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0199. Min Act: -0.0003

Data Index: 1034851 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0202. Min Act: -0.0003

Data Index: 763666 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0193. Min Act: -0.0003

Data Index: 1111155 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0189. Min Act: -0.0003

Data Index: 1344458 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0189. Min Act: -0.0002

Data Index: 663394 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0191. Min Act: -0.0003

Data Index: 3942 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0191. Min Act: -0.0002

Data Index: 1324673 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0187. Min Act: -0.0003

Data Index: 4062 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0186. Min Act: -0.0003

Data Index: 1274117 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0189. Min Act: -0.0003

Data Index: 1161511 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0185. Min Act: -0.0003

Data Index: 1340829 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0185. Min Act: -0.0003

Data Index: 745873 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0184. Min Act: -0.0003

Data Index: 614520 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0184. Min Act: -0.0003

Data Index: 1081349 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0183. Min Act: -0.0003

Data Index: 327132 (C4 (Web Text))

Max Activating Token Index: 61