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

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

Neuron 2706 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0567. Min Act: -0.0000

Data Index: 1522538 (Python Code)

Max Activating Token Index: 898

Text #1

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0456. Min Act: -0.0000

Data Index: 568691 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0412. Min Act: -0.0000

Data Index: 1551810 (Python Code)

Max Activating Token Index: 747

Text #3

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0347. Min Act: -0.0000

Data Index: 1566066 (Python Code)

Max Activating Token Index: 836

Text #4

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0362. Min Act: -0.0000

Data Index: 1540790 (Python Code)

Max Activating Token Index: 634

Text #5

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0348. Min Act: -0.0000

Data Index: 611240 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0335. Min Act: -0.0000

Data Index: 1239318 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0353. Min Act: -0.0000

Data Index: 878921 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0341. Min Act: -0.0000

Data Index: 1636262 (Python Code)

Max Activating Token Index: 587

Text #9

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0365. Min Act: -0.0000

Data Index: 1392380 (Python Code)

Max Activating Token Index: 866

Text #10

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0338. Min Act: -0.0000

Data Index: 1579925 (Python Code)

Max Activating Token Index: 578

Text #11

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0353. Min Act: -0.0000

Data Index: 1538141 (Python Code)

Max Activating Token Index: 129

Text #12

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0360. Min Act: -0.0000

Data Index: 399595 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0341. Min Act: -0.0000

Data Index: 1300656 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0338. Min Act: -0.0000

Data Index: 1307682 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0329. Min Act: -0.0000

Data Index: 1528213 (Python Code)

Max Activating Token Index: 787

Text #16

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0326. Min Act: -0.0000

Data Index: 1608466 (Python Code)

Max Activating Token Index: 305

Text #17

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0315. Min Act: -0.0000

Data Index: 1629248 (Python Code)

Max Activating Token Index: 322

Text #18

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0334. Min Act: -0.0000

Data Index: 142314 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0326. Min Act: -0.0000

Data Index: 272921 (C4 (Web Text))

Max Activating Token Index: 929