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

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

Neuron 1355 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: 0.0454. Min Range: -0.0454

Max Act: 0.0454. Min Act: -0.0006

Data Index: 494703 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0452. Min Act: -0.0006

Data Index: 616109 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0451. Min Act: -0.0006

Data Index: 339204 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0443. Min Act: -0.0006

Data Index: 657572 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0418. Min Act: -0.0006

Data Index: 908740 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0434. Min Act: -0.0006

Data Index: 1197798 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0417. Min Act: -0.0006

Data Index: 377626 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0407. Min Act: -0.0006

Data Index: 979476 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0412. Min Act: -0.0005

Data Index: 546085 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0434. Min Act: -0.0006

Data Index: 585918 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0403. Min Act: -0.0006

Data Index: 364860 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0394. Min Act: -0.0006

Data Index: 529684 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0402. Min Act: -0.0006

Data Index: 832948 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0395. Min Act: -0.0006

Data Index: 443488 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0393. Min Act: -0.0006

Data Index: 879325 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0394. Min Act: -0.0006

Data Index: 806884 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0384. Min Act: -0.0006

Data Index: 444260 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0380. Min Act: -0.0006

Data Index: 31480 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0384. Min Act: -0.0006

Data Index: 394803 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0393. Min Act: -0.0006

Data Index: 1138920 (C4 (Web Text))

Max Activating Token Index: 96