Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4587 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0401. Min Act: -0.0000

Data Index: 718021 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0421. Min Act: -0.0000

Data Index: 1077303 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0378. Min Act: -0.0000

Data Index: 841438 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0407. Min Act: -0.0000

Data Index: 714476 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0397. Min Act: -0.0000

Data Index: 145274 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0378. Min Act: -0.0000

Data Index: 741926 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0385. Min Act: -0.0000

Data Index: 591488 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0379. Min Act: -0.0000

Data Index: 1344734 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0340. Min Act: -0.0000

Data Index: 243427 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0370. Min Act: -0.0000

Data Index: 338662 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0343. Min Act: -0.0000

Data Index: 383759 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0342. Min Act: -0.0000

Data Index: 1305034 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0341. Min Act: -0.0000

Data Index: 1062777 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0350. Min Act: -0.0000

Data Index: 1091295 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0344. Min Act: -0.0000

Data Index: 223218 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0366. Min Act: -0.0000

Data Index: 1568966 (Python Code)

Max Activating Token Index: 248

Text #16

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0345. Min Act: -0.0000

Data Index: 448377 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0323. Min Act: -0.0001

Data Index: 905513 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0386. Min Act: -0.0001

Data Index: 1068849 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0322. Min Act: -0.0000

Data Index: 71378 (C4 (Web Text))

Max Activating Token Index: 863