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

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

Neuron 20 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: 1023902 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0215. Min Act: -0.0006

Data Index: 854975 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0214. Min Act: -0.0006

Data Index: 162205 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0214. Min Act: -0.0006

Data Index: 960732 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0203. Min Act: -0.0006

Data Index: 454927 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0215. Min Act: -0.0006

Data Index: 429295 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0206. Min Act: -0.0006

Data Index: 1006842 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0210. Min Act: -0.0006

Data Index: 1348103 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1270638 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0208. Min Act: -0.0006

Data Index: 1306636 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0208. Min Act: -0.0006

Data Index: 868959 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0207. Min Act: -0.0006

Data Index: 384457 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0207. Min Act: -0.0006

Data Index: 1019350 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0207. Min Act: -0.0006

Data Index: 180680 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0206. Min Act: -0.0006

Data Index: 1231443 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0205. Min Act: -0.0006

Data Index: 282177 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0205. Min Act: -0.0006

Data Index: 850390 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0200. Min Act: -0.0006

Data Index: 325869 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0203. Min Act: -0.0006

Data Index: 104727 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0203. Min Act: -0.0006

Data Index: 305179 (C4 (Web Text))

Max Activating Token Index: 910