Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 272 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0407. Min Act: -0.0001

Data Index: 10971 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0400. Min Act: -0.0001

Data Index: 457431 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0369. Min Act: -0.0001

Data Index: 1438077 (Python Code)

Max Activating Token Index: 43

Text #3

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0343. Min Act: -0.0001

Data Index: 138828 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0378. Min Act: -0.0000

Data Index: 297331 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0362. Min Act: -0.0000

Data Index: 1541697 (Python Code)

Max Activating Token Index: 204

Text #6

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0347. Min Act: -0.0000

Data Index: 1620593 (Python Code)

Max Activating Token Index: 813

Text #7

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0345. Min Act: -0.0001

Data Index: 745053 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0368. Min Act: -0.0001

Data Index: 1545545 (Python Code)

Max Activating Token Index: 761

Text #9

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0341. Min Act: -0.0001

Data Index: 808879 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0361. Min Act: -0.0000

Data Index: 1484574 (Python Code)

Max Activating Token Index: 172

Text #11

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0321. Min Act: -0.0000

Data Index: 1512059 (Python Code)

Max Activating Token Index: 798

Text #12

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0343. Min Act: -0.0001

Data Index: 698920 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0316. Min Act: -0.0001

Data Index: 1077180 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0326. Min Act: -0.0001

Data Index: 7818 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0339. Min Act: -0.0000

Data Index: 164080 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0336. Min Act: -0.0001

Data Index: 1552347 (Python Code)

Max Activating Token Index: 969

Text #17

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0342. Min Act: -0.0001

Data Index: 504018 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0323. Min Act: -0.0000

Data Index: 1368196 (Python Code)

Max Activating Token Index: 868

Text #19

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0305. Min Act: -0.0001

Data Index: 1004280 (C4 (Web Text))

Max Activating Token Index: 463