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

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

Neuron 1587 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0002

Data Index: 17830 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0313. Min Act: -0.0003

Data Index: 849468 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0295. Min Act: -0.0002

Data Index: 1241426 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0287. Min Act: -0.0002

Data Index: 509468 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0282. Min Act: -0.0002

Data Index: 277738 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0285. Min Act: -0.0003

Data Index: 840059 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0275. Min Act: -0.0004

Data Index: 542647 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0278. Min Act: -0.0003

Data Index: 805835 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0269. Min Act: -0.0003

Data Index: 945682 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0277. Min Act: -0.0002

Data Index: 1346802 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0269. Min Act: -0.0003

Data Index: 51531 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0269. Min Act: -0.0003

Data Index: 543419 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0264. Min Act: -0.0003

Data Index: 1025303 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1335342 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0256. Min Act: -0.0002

Data Index: 596950 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0264. Min Act: -0.0002

Data Index: 567298 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0265. Min Act: -0.0003

Data Index: 14828 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0266. Min Act: -0.0003

Data Index: 775879 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0270. Min Act: -0.0003

Data Index: 541972 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0260. Min Act: -0.0003

Data Index: 182212 (C4 (Web Text))

Max Activating Token Index: 228