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

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

Neuron 3297 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1650822 (Python Code)

Max Activating Token Index: 704

Text #1

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1462724 (Python Code)

Max Activating Token Index: 738

Text #2

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1532257 (Python Code)

Max Activating Token Index: 423

Text #3

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0356. Min Act: -0.0002

Data Index: 543643 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1389287 (Python Code)

Max Activating Token Index: 367

Text #5

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1059215 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1525167 (Python Code)

Max Activating Token Index: 536

Text #7

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1298705 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1002513 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0306. Min Act: -0.0002

Data Index: 1112594 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1501707 (Python Code)

Max Activating Token Index: 327

Text #11

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0283. Min Act: -0.0002

Data Index: 810510 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1416463 (Python Code)

Max Activating Token Index: 28

Text #13

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0289. Min Act: -0.0002

Data Index: 1536532 (Python Code)

Max Activating Token Index: 267

Text #14

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0300. Min Act: -0.0002

Data Index: 904075 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0317. Min Act: -0.0002

Data Index: 425728 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0298. Min Act: -0.0002

Data Index: 1513503 (Python Code)

Max Activating Token Index: 330

Text #17

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1158020 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0306. Min Act: -0.0002

Data Index: 1428596 (Python Code)

Max Activating Token Index: 880

Text #19

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1574870 (Python Code)

Max Activating Token Index: 342