Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 662 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0455. Min Act: -0.0000

Data Index: 666258 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0388. Min Act: -0.0000

Data Index: 1014175 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0429. Min Act: -0.0000

Data Index: 484971 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0408. Min Act: -0.0000

Data Index: 171985 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0434. Min Act: -0.0000

Data Index: 8867 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0374. Min Act: -0.0000

Data Index: 827527 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0332. Min Act: -0.0000

Data Index: 1192948 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0384. Min Act: -0.0000

Data Index: 924773 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0358. Min Act: -0.0001

Data Index: 1590947 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0346. Min Act: -0.0000

Data Index: 943025 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0346. Min Act: -0.0000

Data Index: 919563 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0341. Min Act: -0.0000

Data Index: 1344976 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0351. Min Act: -0.0000

Data Index: 1117661 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0376. Min Act: -0.0000

Data Index: 154130 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0310. Min Act: -0.0000

Data Index: 994465 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0359. Min Act: -0.0000

Data Index: 1196826 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0348. Min Act: -0.0000

Data Index: 970761 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0357. Min Act: -0.0000

Data Index: 1144663 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0330. Min Act: -0.0000

Data Index: 785941 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0302. Min Act: -0.0000

Data Index: 135599 (C4 (Web Text))

Max Activating Token Index: 432