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

Dataset: The Pile

Neuron 4889 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0442. Min Act: 0.0000

Data Index: 1319417 (The Pile)

Max Activating Token Index: 2

Text #1

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0442. Min Act: 0.0000

Data Index: 1270842 (The Pile)

Max Activating Token Index: 2

Text #2

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0427. Min Act: -0.0000

Data Index: 886986 (The Pile)

Max Activating Token Index: 2

Text #3

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0427. Min Act: 0.0000

Data Index: 767797 (The Pile)

Max Activating Token Index: 2

Text #4

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0393. Min Act: -0.0000

Data Index: 1417252 (The Pile)

Max Activating Token Index: 2

Text #5

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0361. Min Act: 0.0000

Data Index: 754630 (The Pile)

Max Activating Token Index: 18

Text #6

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0345. Min Act: 0.0000

Data Index: 1570879 (The Pile)

Max Activating Token Index: 477

Text #7

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0354. Min Act: -0.0000

Data Index: 751226 (The Pile)

Max Activating Token Index: 2

Text #8

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0356. Min Act: -0.0000

Data Index: 748106 (The Pile)

Max Activating Token Index: 2

Text #9

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0337. Min Act: 0.0000

Data Index: 329632 (The Pile)

Max Activating Token Index: 18

Text #10

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0336. Min Act: -0.0000

Data Index: 32743 (The Pile)

Max Activating Token Index: 24

Text #11

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0336. Min Act: -0.0000

Data Index: 817518 (The Pile)

Max Activating Token Index: 2

Text #12

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0333. Min Act: -0.0000

Data Index: 545377 (The Pile)

Max Activating Token Index: 18

Text #13

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0330. Min Act: 0.0000

Data Index: 1790229 (The Pile)

Max Activating Token Index: 27

Text #14

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0328. Min Act: 0.0000

Data Index: 555411 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0328. Min Act: 0.0000

Data Index: 402765 (The Pile)

Max Activating Token Index: 88

Text #16

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0323. Min Act: 0.0000

Data Index: 565818 (The Pile)

Max Activating Token Index: 194

Text #17

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0321. Min Act: 0.0000

Data Index: 1242392 (The Pile)

Max Activating Token Index: 7

Text #18

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0318. Min Act: -0.0000

Data Index: 1328287 (The Pile)

Max Activating Token Index: 4

Text #19

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0317. Min Act: 0.0000

Data Index: 549733 (The Pile)

Max Activating Token Index: 65