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

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

Neuron 1047 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: 0.0368. Min Range: -0.0368

Max Act: 0.0368. Min Act: -0.0003

Data Index: 981250 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1085925 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0356. Min Act: -0.0003

Data Index: 549952 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0330. Min Act: -0.0003

Data Index: 626999 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0324. Min Act: -0.0003

Data Index: 348485 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0325. Min Act: -0.0003

Data Index: 1324051 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0312. Min Act: -0.0003

Data Index: 285042 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0309. Min Act: -0.0003

Data Index: 1121940 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0315. Min Act: -0.0003

Data Index: 704060 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0316. Min Act: -0.0003

Data Index: 590116 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0310. Min Act: -0.0003

Data Index: 1351994 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0308. Min Act: -0.0003

Data Index: 609689 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0304. Min Act: -0.0003

Data Index: 1180937 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1036153 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0297. Min Act: -0.0003

Data Index: 995754 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0298. Min Act: -0.0004

Data Index: 955892 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0315. Min Act: -0.0003

Data Index: 386729 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1164787 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0293. Min Act: -0.0003

Data Index: 1153311 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0298. Min Act: -0.0003

Data Index: 789554 (C4 (Web Text))

Max Activating Token Index: 93