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

Dataset: The Pile

Neuron 1006 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: 0.0347. Min Range: -0.0347

Max Act: 0.0347. Min Act: 0.0000

Data Index: 942400 (The Pile)

Max Activating Token Index: 1009

Text #1

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0328. Min Act: -0.0000

Data Index: 177688 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0309. Min Act: 0.0000

Data Index: 993294 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0260. Min Act: 0.0000

Data Index: 204624 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0259. Min Act: -0.0000

Data Index: 714714 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0259. Min Act: -0.0000

Data Index: 1495676 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0252. Min Act: -0.0000

Data Index: 126950 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0248. Min Act: 0.0000

Data Index: 635149 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0240. Min Act: 0.0000

Data Index: 1764941 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0240. Min Act: -0.0000

Data Index: 471846 (The Pile)

Max Activating Token Index: 1013

Text #10

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0239. Min Act: -0.0000

Data Index: 1497277 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0239. Min Act: 0.0000

Data Index: 877260 (The Pile)

Max Activating Token Index: 975

Text #12

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0236. Min Act: 0.0000

Data Index: 238088 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0236. Min Act: -0.0000

Data Index: 371342 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0235. Min Act: -0.0000

Data Index: 1272114 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0234. Min Act: -0.0000

Data Index: 1723138 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0234. Min Act: 0.0000

Data Index: 1576132 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0234. Min Act: -0.0000

Data Index: 1035770 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0233. Min Act: -0.0000

Data Index: 1142641 (The Pile)

Max Activating Token Index: 992

Text #19

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0231. Min Act: -0.0000

Data Index: 1595130 (The Pile)

Max Activating Token Index: 1022