Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3808 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0321. Min Act: -0.0003

Data Index: 1095218 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0336. Min Act: -0.0003

Data Index: 949976 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0305. Min Act: -0.0003

Data Index: 1232110 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0295. Min Act: -0.0003

Data Index: 603918 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0301. Min Act: -0.0003

Data Index: 112150 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1269638 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1487813 (Python Code)

Max Activating Token Index: 36

Text #7

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0313. Min Act: -0.0003

Data Index: 26629 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0261. Min Act: -0.0003

Data Index: 1333412 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0279. Min Act: -0.0004

Data Index: 1334531 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1654748 (Python Code)

Max Activating Token Index: 16

Text #11

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0281. Min Act: -0.0003

Data Index: 220153 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0293. Min Act: -0.0003

Data Index: 928179 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0282. Min Act: -0.0003

Data Index: 1566798 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0300. Min Act: -0.0003

Data Index: 1618720 (Python Code)

Max Activating Token Index: 220

Text #15

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0266. Min Act: -0.0003

Data Index: 694279 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0278. Min Act: -0.0003

Data Index: 235286 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0260. Min Act: -0.0003

Data Index: 1603149 (Python Code)

Max Activating Token Index: 723

Text #18

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0280. Min Act: -0.0003

Data Index: 491686 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0280. Min Act: -0.0003

Data Index: 1389306 (Python Code)

Max Activating Token Index: 6