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

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

Neuron 1615 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: 0.0473. Min Range: -0.0473

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1109013 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0451. Min Act: -0.0001

Data Index: 79608 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0439. Min Act: -0.0003

Data Index: 1276039 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1040374 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0402. Min Act: -0.0002

Data Index: 88802 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0383. Min Act: -0.0003

Data Index: 1504307 (Python Code)

Max Activating Token Index: 252

Text #6

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1150760 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0380. Min Act: -0.0003

Data Index: 7015 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0378. Min Act: -0.0001

Data Index: 406903 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0375. Min Act: -0.0003

Data Index: 1513886 (Python Code)

Max Activating Token Index: 53

Text #10

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1434566 (Python Code)

Max Activating Token Index: 105

Text #11

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0363. Min Act: -0.0002

Data Index: 370261 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1006914 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0359. Min Act: -0.0003

Data Index: 1104 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0357. Min Act: -0.0003

Data Index: 343165 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0366. Min Act: -0.0001

Data Index: 18364 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0361. Min Act: -0.0003

Data Index: 1021979 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0353. Min Act: -0.0002

Data Index: 1155155 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0351. Min Act: -0.0002

Data Index: 470056 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0348. Min Act: -0.0003

Data Index: 1212554 (C4 (Web Text))

Max Activating Token Index: 877