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

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

Neuron 3220 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0510. Min Act: -0.0000

Data Index: 1240556 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0387. Min Act: -0.0000

Data Index: 934563 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0400. Min Act: -0.0000

Data Index: 95992 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0377. Min Act: -0.0000

Data Index: 1327736 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0359. Min Act: -0.0000

Data Index: 710071 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0360. Min Act: -0.0000

Data Index: 1314005 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0352. Min Act: -0.0000

Data Index: 425475 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0341. Min Act: -0.0000

Data Index: 192606 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0326. Min Act: -0.0000

Data Index: 702240 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0349. Min Act: -0.0000

Data Index: 1321845 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0350. Min Act: -0.0000

Data Index: 56513 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0346. Min Act: -0.0000

Data Index: 556337 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0315. Min Act: -0.0000

Data Index: 831401 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0314. Min Act: -0.0000

Data Index: 829480 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0322. Min Act: -0.0000

Data Index: 1539937 (Python Code)

Max Activating Token Index: 503

Text #15

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0321. Min Act: -0.0000

Data Index: 62301 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0315. Min Act: -0.0000

Data Index: 824398 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0323. Min Act: -0.0000

Data Index: 734284 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0306. Min Act: -0.0000

Data Index: 727386 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0288. Min Act: -0.0000

Data Index: 733458 (C4 (Web Text))

Max Activating Token Index: 844