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

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

Neuron 1394 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: 0.0580. Min Range: -0.0580

Max Act: 0.0580. Min Act: -0.0006

Data Index: 1635402 (Python Code)

Max Activating Token Index: 264

Text #1

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0481. Min Act: -0.0006

Data Index: 415574 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0438. Min Act: -0.0006

Data Index: 792622 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0417. Min Act: -0.0006

Data Index: 8017 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0397. Min Act: -0.0006

Data Index: 278303 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0421. Min Act: -0.0006

Data Index: 1388597 (Python Code)

Max Activating Token Index: 231

Text #6

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0383. Min Act: -0.0006

Data Index: 1386045 (Python Code)

Max Activating Token Index: 136

Text #7

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0390. Min Act: -0.0006

Data Index: 901231 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0390. Min Act: -0.0006

Data Index: 781497 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0364. Min Act: -0.0006

Data Index: 223472 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0384. Min Act: -0.0006

Data Index: 121613 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0380. Min Act: -0.0006

Data Index: 1326641 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0362. Min Act: -0.0006

Data Index: 1084708 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0350. Min Act: -0.0006

Data Index: 1327114 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0363. Min Act: -0.0006

Data Index: 1602657 (Python Code)

Max Activating Token Index: 209

Text #15

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0346. Min Act: -0.0006

Data Index: 1142217 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0350. Min Act: -0.0006

Data Index: 822005 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0356. Min Act: -0.0006

Data Index: 802812 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0351. Min Act: -0.0006

Data Index: 1233177 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0360. Min Act: -0.0006

Data Index: 315084 (C4 (Web Text))

Max Activating Token Index: 964