Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4723 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0281. Min Act: -0.0002

Data Index: 1421902 (Python Code)

Max Activating Token Index: 734

Text #1

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0263. Min Act: -0.0003

Data Index: 293750 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1445620 (Python Code)

Max Activating Token Index: 334

Text #3

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1463232 (Python Code)

Max Activating Token Index: 64

Text #4

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1575051 (Python Code)

Max Activating Token Index: 141

Text #5

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0256. Min Act: -0.0002

Data Index: 291572 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1534428 (Python Code)

Max Activating Token Index: 154

Text #7

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0235. Min Act: -0.0002

Data Index: 371806 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1508845 (Python Code)

Max Activating Token Index: 150

Text #9

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0232. Min Act: -0.0003

Data Index: 1221235 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0227. Min Act: -0.0002

Data Index: 1373591 (Python Code)

Max Activating Token Index: 328

Text #11

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1282142 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0224. Min Act: -0.0002

Data Index: 973256 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0219. Min Act: -0.0002

Data Index: 1604989 (Python Code)

Max Activating Token Index: 961

Text #14

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0211. Min Act: -0.0002

Data Index: 1294614 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1464694 (Python Code)

Max Activating Token Index: 71

Text #16

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1408407 (Python Code)

Max Activating Token Index: 22

Text #17

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0211. Min Act: -0.0003

Data Index: 932066 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1397927 (Python Code)

Max Activating Token Index: 87

Text #19

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0211. Min Act: -0.0002

Data Index: 1611898 (Python Code)

Max Activating Token Index: 418