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

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

Neuron 1949 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: 0.0414. Min Range: -0.0414

Max Act: 0.0414. Min Act: -0.0003

Data Index: 1119627 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0414. Min Act: -0.0002

Data Index: 166088 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0389. Min Act: -0.0003

Data Index: 428136 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0387. Min Act: -0.0003

Data Index: 638696 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0368. Min Act: -0.0003

Data Index: 523148 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0359. Min Act: -0.0004

Data Index: 1091884 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0360. Min Act: -0.0003

Data Index: 1216667 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0368. Min Act: -0.0003

Data Index: 560316 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0371. Min Act: -0.0003

Data Index: 378764 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0360. Min Act: -0.0003

Data Index: 208920 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0372. Min Act: -0.0002

Data Index: 708746 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0351. Min Act: -0.0003

Data Index: 939836 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0337. Min Act: -0.0003

Data Index: 335957 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0342. Min Act: -0.0003

Data Index: 645689 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0346. Min Act: -0.0003

Data Index: 304251 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0339. Min Act: -0.0003

Data Index: 933541 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0340. Min Act: -0.0002

Data Index: 91577 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1255420 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0344. Min Act: -0.0003

Data Index: 1243785 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0342. Min Act: -0.0003

Data Index: 670422 (C4 (Web Text))

Max Activating Token Index: 332