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

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

Neuron 1946 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: 0.0409. Min Range: -0.0409

Max Act: 0.0409. Min Act: -0.0003

Data Index: 1184694 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1514383 (Python Code)

Max Activating Token Index: 84

Text #2

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0390. Min Act: -0.0003

Data Index: 1535822 (Python Code)

Max Activating Token Index: 350

Text #3

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0382. Min Act: -0.0002

Data Index: 918428 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0363. Min Act: -0.0003

Data Index: 1606505 (Python Code)

Max Activating Token Index: 241

Text #5

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0350. Min Act: -0.0002

Data Index: 173466 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0369. Min Act: -0.0002

Data Index: 408124 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0361. Min Act: -0.0002

Data Index: 338014 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0362. Min Act: -0.0003

Data Index: 835529 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1556990 (Python Code)

Max Activating Token Index: 874

Text #10

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0354. Min Act: -0.0002

Data Index: 897136 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0354. Min Act: -0.0003

Data Index: 951452 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0344. Min Act: -0.0003

Data Index: 1452247 (Python Code)

Max Activating Token Index: 260

Text #13

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0345. Min Act: -0.0003

Data Index: 659088 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0351. Min Act: -0.0002

Data Index: 618599 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0338. Min Act: -0.0002

Data Index: 730904 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0333. Min Act: -0.0003

Data Index: 654065 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0324. Min Act: -0.0003

Data Index: 657790 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0326. Min Act: -0.0003

Data Index: 169193 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0331. Min Act: -0.0003

Data Index: 1447624 (Python Code)

Max Activating Token Index: 345