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

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

Neuron 654 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: 0.0288. Min Range: -0.0288

Max Act: 0.0287. Min Act: -0.0006

Data Index: 1504832 (Python Code)

Max Activating Token Index: 207

Text #1

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0284. Min Act: -0.0006

Data Index: 478645 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0283. Min Act: -0.0006

Data Index: 1580252 (Python Code)

Max Activating Token Index: 590

Text #3

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0288. Min Act: -0.0006

Data Index: 1552447 (Python Code)

Max Activating Token Index: 422

Text #4

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0260. Min Act: -0.0006

Data Index: 120465 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0263. Min Act: -0.0006

Data Index: 1563922 (Python Code)

Max Activating Token Index: 337

Text #6

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0272. Min Act: -0.0006

Data Index: 370408 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0263. Min Act: -0.0006

Data Index: 837652 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0276. Min Act: -0.0006

Data Index: 1418861 (Python Code)

Max Activating Token Index: 868

Text #9

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0256. Min Act: -0.0006

Data Index: 1528799 (Python Code)

Max Activating Token Index: 825

Text #10

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0257. Min Act: -0.0006

Data Index: 1514162 (Python Code)

Max Activating Token Index: 192

Text #11

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0245. Min Act: -0.0006

Data Index: 1517379 (Python Code)

Max Activating Token Index: 944

Text #12

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0256. Min Act: -0.0006

Data Index: 1462889 (Python Code)

Max Activating Token Index: 312

Text #13

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0248. Min Act: -0.0006

Data Index: 1098723 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0248. Min Act: -0.0006

Data Index: 274633 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0242. Min Act: -0.0006

Data Index: 361133 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0253. Min Act: -0.0006

Data Index: 1213626 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0234. Min Act: -0.0006

Data Index: 198747 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0237. Min Act: -0.0006

Data Index: 1589688 (Python Code)

Max Activating Token Index: 433

Text #19

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0238. Min Act: -0.0006

Data Index: 440744 (C4 (Web Text))

Max Activating Token Index: 879