Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3045 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0398. Min Act: -0.0002

Data Index: 1545403 (Python Code)

Max Activating Token Index: 592

Text #1

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0377. Min Act: -0.0002

Data Index: 653608 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0349. Min Act: -0.0002

Data Index: 746854 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0345. Min Act: -0.0002

Data Index: 662619 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1353018 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0340. Min Act: -0.0002

Data Index: 112987 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1048498 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1651713 (Python Code)

Max Activating Token Index: 642

Text #8

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0306. Min Act: -0.0002

Data Index: 1376100 (Python Code)

Max Activating Token Index: 561

Text #9

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1522786 (Python Code)

Max Activating Token Index: 317

Text #10

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0297. Min Act: -0.0002

Data Index: 683823 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0301. Min Act: -0.0002

Data Index: 1574773 (Python Code)

Max Activating Token Index: 500

Text #12

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0296. Min Act: -0.0002

Data Index: 529948 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0290. Min Act: -0.0002

Data Index: 848256 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0289. Min Act: -0.0002

Data Index: 1424108 (Python Code)

Max Activating Token Index: 654

Text #15

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0296. Min Act: -0.0002

Data Index: 140828 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0293. Min Act: -0.0002

Data Index: 1471973 (Python Code)

Max Activating Token Index: 846

Text #17

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1053135 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1619812 (Python Code)

Max Activating Token Index: 391

Text #19

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0293. Min Act: -0.0002

Data Index: 1015550 (C4 (Web Text))

Max Activating Token Index: 393