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

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

Neuron 853 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: 0.0524. Min Range: -0.0524

Max Act: 0.0521. Min Act: -0.0002

Data Index: 18670 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0517. Min Act: -0.0003

Data Index: 193022 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0524. Min Act: -0.0002

Data Index: 396566 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0492. Min Act: -0.0002

Data Index: 333378 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0472. Min Act: -0.0003

Data Index: 270895 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0473. Min Act: -0.0002

Data Index: 387746 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0459. Min Act: -0.0003

Data Index: 185561 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0445. Min Act: -0.0003

Data Index: 958045 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0435. Min Act: 0.0000

Data Index: 350630 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0438. Min Act: -0.0003

Data Index: 657436 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1008923 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0441. Min Act: -0.0003

Data Index: 412995 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0443. Min Act: -0.0003

Data Index: 119791 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0434. Min Act: -0.0001

Data Index: 38 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0436. Min Act: -0.0003

Data Index: 123936 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0426. Min Act: -0.0003

Data Index: 823640 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0410. Min Act: -0.0003

Data Index: 816419 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0426. Min Act: -0.0002

Data Index: 292097 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0425. Min Act: -0.0002

Data Index: 52165 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0428. Min Act: -0.0003

Data Index: 443318 (C4 (Web Text))

Max Activating Token Index: 141