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

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

Neuron 299 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: 0.0396. Min Range: -0.0396

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1606349 (Python Code)

Max Activating Token Index: 860

Text #1

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0390. Min Act: -0.0003

Data Index: 1639672 (Python Code)

Max Activating Token Index: 932

Text #2

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0384. Min Act: -0.0003

Data Index: 1550417 (Python Code)

Max Activating Token Index: 811

Text #3

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0376. Min Act: -0.0004

Data Index: 1461774 (Python Code)

Max Activating Token Index: 265

Text #4

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0376. Min Act: -0.0003

Data Index: 489564 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0382. Min Act: -0.0003

Data Index: 481747 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0352. Min Act: -0.0003

Data Index: 195567 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0356. Min Act: -0.0002

Data Index: 606972 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0370. Min Act: -0.0003

Data Index: 1201231 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0354. Min Act: -0.0004

Data Index: 903835 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0345. Min Act: -0.0003

Data Index: 377116 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0330. Min Act: -0.0003

Data Index: 1551541 (Python Code)

Max Activating Token Index: 448

Text #12

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0324. Min Act: -0.0003

Data Index: 872690 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0329. Min Act: -0.0003

Data Index: 1573389 (Python Code)

Max Activating Token Index: 720

Text #14

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0306. Min Act: -0.0002

Data Index: 1469398 (Python Code)

Max Activating Token Index: 132

Text #15

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0311. Min Act: -0.0003

Data Index: 91342 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0317. Min Act: -0.0003

Data Index: 137588 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0318. Min Act: -0.0003

Data Index: 1026691 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1480240 (Python Code)

Max Activating Token Index: 287

Text #19

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0309. Min Act: -0.0004

Data Index: 1524844 (Python Code)

Max Activating Token Index: 315