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

Dataset: The Pile

Neuron 3565 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: 0.0380. Min Range: -0.0380

Max Act: 0.0380. Min Act: 0.0000

Data Index: 651636 (The Pile)

Max Activating Token Index: 21

Text #1

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0373. Min Act: 0.0000

Data Index: 556490 (The Pile)

Max Activating Token Index: 3

Text #2

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0373. Min Act: -0.0000

Data Index: 527776 (The Pile)

Max Activating Token Index: 31

Text #3

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0365. Min Act: 0.0000

Data Index: 717219 (The Pile)

Max Activating Token Index: 3

Text #4

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0362. Min Act: 0.0000

Data Index: 1096211 (The Pile)

Max Activating Token Index: 3

Text #5

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0357. Min Act: 0.0000

Data Index: 885723 (The Pile)

Max Activating Token Index: 31

Text #6

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0356. Min Act: -0.0000

Data Index: 756162 (The Pile)

Max Activating Token Index: 6

Text #7

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0355. Min Act: -0.0000

Data Index: 1689289 (The Pile)

Max Activating Token Index: 31

Text #8

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0353. Min Act: 0.0000

Data Index: 786203 (The Pile)

Max Activating Token Index: 6

Text #9

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0352. Min Act: -0.0000

Data Index: 118040 (The Pile)

Max Activating Token Index: 17

Text #10

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0347. Min Act: 0.0000

Data Index: 223982 (The Pile)

Max Activating Token Index: 77

Text #11

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0345. Min Act: 0.0000

Data Index: 1026365 (The Pile)

Max Activating Token Index: 46

Text #12

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0343. Min Act: 0.0000

Data Index: 1716441 (The Pile)

Max Activating Token Index: 2

Text #13

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0343. Min Act: 0.0000

Data Index: 1106716 (The Pile)

Max Activating Token Index: 2

Text #14

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0343. Min Act: 0.0000

Data Index: 462826 (The Pile)

Max Activating Token Index: 19

Text #15

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0339. Min Act: 0.0000

Data Index: 1591415 (The Pile)

Max Activating Token Index: 23

Text #16

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0337. Min Act: 0.0000

Data Index: 789209 (The Pile)

Max Activating Token Index: 32

Text #17

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0336. Min Act: 0.0000

Data Index: 811995 (The Pile)

Max Activating Token Index: 74

Text #18

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0335. Min Act: -0.0000

Data Index: 1852774 (The Pile)

Max Activating Token Index: 29

Text #19

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0335. Min Act: 0.0000

Data Index: 1826758 (The Pile)

Max Activating Token Index: 31