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

Dataset: The Pile

Neuron 3462 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: 0.0305. Min Range: -0.0305

Max Act: 0.0302. Min Act: 0.0000

Data Index: 1201142 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0301. Min Act: -0.0000

Data Index: 928516 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0294. Min Act: -0.0000

Data Index: 315010 (The Pile)

Max Activating Token Index: 96

Text #3

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0305. Min Act: -0.0000

Data Index: 1908710 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0293. Min Act: -0.0000

Data Index: 1981828 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0282. Min Act: -0.0000

Data Index: 1394460 (The Pile)

Max Activating Token Index: 21

Text #6

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0291. Min Act: -0.0000

Data Index: 58824 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0291. Min Act: -0.0000

Data Index: 1645946 (The Pile)

Max Activating Token Index: 20

Text #8

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0290. Min Act: 0.0000

Data Index: 1959126 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0289. Min Act: 0.0000

Data Index: 1761216 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0288. Min Act: -0.0000

Data Index: 258140 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0287. Min Act: 0.0000

Data Index: 9582 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0286. Min Act: -0.0000

Data Index: 133368 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0286. Min Act: -0.0000

Data Index: 321717 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0285. Min Act: -0.0000

Data Index: 1186606 (The Pile)

Max Activating Token Index: 169

Text #15

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0285. Min Act: 0.0000

Data Index: 352513 (The Pile)

Max Activating Token Index: 7

Text #16

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0284. Min Act: 0.0000

Data Index: 857295 (The Pile)

Max Activating Token Index: 968

Text #17

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0284. Min Act: -0.0000

Data Index: 1676076 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0280. Min Act: -0.0000

Data Index: 143331 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0280. Min Act: 0.0000

Data Index: 1018805 (The Pile)

Max Activating Token Index: 1023