Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1569 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0327. Min Act: -0.0005

Data Index: 52544 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0320. Min Act: -0.0005

Data Index: 934425 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0318. Min Act: -0.0004

Data Index: 476053 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0323. Min Act: -0.0005

Data Index: 582337 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0309. Min Act: -0.0005

Data Index: 748658 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0304. Min Act: -0.0005

Data Index: 1180627 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0304. Min Act: -0.0005

Data Index: 31780 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0292. Min Act: -0.0005

Data Index: 122012 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0286. Min Act: -0.0005

Data Index: 354060 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0291. Min Act: -0.0004

Data Index: 268181 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0278. Min Act: -0.0005

Data Index: 5717 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0291. Min Act: -0.0005

Data Index: 1250109 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0281. Min Act: -0.0005

Data Index: 681445 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0277. Min Act: -0.0005

Data Index: 386090 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0271. Min Act: -0.0005

Data Index: 442658 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0276. Min Act: -0.0005

Data Index: 308162 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0269. Min Act: -0.0005

Data Index: 162535 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0281. Min Act: -0.0005

Data Index: 1313571 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0275. Min Act: -0.0005

Data Index: 581771 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0274. Min Act: -0.0005

Data Index: 620435 (C4 (Web Text))

Max Activating Token Index: 276