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

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

Neuron 643 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0376. Min Act: -0.0006

Data Index: 1615373 (Python Code)

Max Activating Token Index: 935

Text #1

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0327. Min Act: -0.0005

Data Index: 198848 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0349. Min Act: -0.0005

Data Index: 1247619 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0333. Min Act: -0.0006

Data Index: 1427972 (Python Code)

Max Activating Token Index: 677

Text #4

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0320. Min Act: -0.0005

Data Index: 541578 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0340. Min Act: -0.0006

Data Index: 1592203 (Python Code)

Max Activating Token Index: 499

Text #6

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0346. Min Act: -0.0005

Data Index: 1051932 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0316. Min Act: -0.0006

Data Index: 1597852 (Python Code)

Max Activating Token Index: 749

Text #8

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0334. Min Act: -0.0006

Data Index: 1106610 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0326. Min Act: -0.0006

Data Index: 1428391 (Python Code)

Max Activating Token Index: 595

Text #10

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0322. Min Act: -0.0005

Data Index: 244977 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0312. Min Act: -0.0006

Data Index: 1076924 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0312. Min Act: -0.0006

Data Index: 1090125 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0288. Min Act: -0.0006

Data Index: 1476439 (Python Code)

Max Activating Token Index: 615

Text #14

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0288. Min Act: -0.0005

Data Index: 1245424 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0286. Min Act: -0.0006

Data Index: 272440 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0297. Min Act: -0.0006

Data Index: 273861 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0303. Min Act: -0.0006

Data Index: 423366 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0309. Min Act: -0.0006

Data Index: 268951 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0309. Min Act: -0.0006

Data Index: 68525 (C4 (Web Text))

Max Activating Token Index: 153