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

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

Neuron 1600 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: 0.0334. Min Range: -0.0334

Max Act: 0.0334. Min Act: -0.0006

Data Index: 534259 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0300. Min Act: -0.0006

Data Index: 87766 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0315. Min Act: -0.0006

Data Index: 1232686 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0307. Min Act: -0.0006

Data Index: 130748 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0291. Min Act: -0.0006

Data Index: 541997 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0284. Min Act: -0.0006

Data Index: 1226613 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0288. Min Act: -0.0006

Data Index: 1323882 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0289. Min Act: -0.0006

Data Index: 835330 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0284. Min Act: -0.0006

Data Index: 246946 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0271. Min Act: -0.0005

Data Index: 169234 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0281. Min Act: -0.0006

Data Index: 600042 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0291. Min Act: -0.0006

Data Index: 981241 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0295. Min Act: -0.0006

Data Index: 357868 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0271. Min Act: -0.0006

Data Index: 59212 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0269. Min Act: -0.0006

Data Index: 278634 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0273. Min Act: -0.0006

Data Index: 513599 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0257. Min Act: -0.0006

Data Index: 1019613 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0261. Min Act: -0.0006

Data Index: 665843 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0266. Min Act: -0.0006

Data Index: 368162 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0235. Min Act: -0.0006

Data Index: 663294 (C4 (Web Text))

Max Activating Token Index: 724