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

Dataset: The Pile

Neuron 1581 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: 0.0238. Min Range: -0.0238

Max Act: 0.0238. Min Act: -0.0000

Data Index: 969450 (The Pile)

Max Activating Token Index: 1002

Text #1

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0219. Min Act: -0.0000

Data Index: 1237096 (The Pile)

Max Activating Token Index: 956

Text #2

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0217. Min Act: -0.0000

Data Index: 300279 (The Pile)

Max Activating Token Index: 972

Text #3

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0217. Min Act: -0.0000

Data Index: 885569 (The Pile)

Max Activating Token Index: 1006

Text #4

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0216. Min Act: -0.0000

Data Index: 1891975 (The Pile)

Max Activating Token Index: 1002

Text #5

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0211. Min Act: -0.0000

Data Index: 1228495 (The Pile)

Max Activating Token Index: 1002

Text #6

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0211. Min Act: -0.0000

Data Index: 1013673 (The Pile)

Max Activating Token Index: 973

Text #7

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0214. Min Act: -0.0000

Data Index: 900103 (The Pile)

Max Activating Token Index: 996

Text #8

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0207. Min Act: -0.0000

Data Index: 201536 (The Pile)

Max Activating Token Index: 1003

Text #9

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0200. Min Act: -0.0000

Data Index: 153898 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0194. Min Act: -0.0000

Data Index: 1747113 (The Pile)

Max Activating Token Index: 1019

Text #11

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0200. Min Act: -0.0000

Data Index: 1981043 (The Pile)

Max Activating Token Index: 953

Text #12

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0191. Min Act: -0.0000

Data Index: 261887 (The Pile)

Max Activating Token Index: 1016

Text #13

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0198. Min Act: -0.0000

Data Index: 212036 (The Pile)

Max Activating Token Index: 923

Text #14

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0189. Min Act: -0.0000

Data Index: 438983 (The Pile)

Max Activating Token Index: 1020

Text #15

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0189. Min Act: -0.0000

Data Index: 1378196 (The Pile)

Max Activating Token Index: 950

Text #16

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0188. Min Act: -0.0000

Data Index: 1774626 (The Pile)

Max Activating Token Index: 966

Text #17

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0186. Min Act: -0.0000

Data Index: 1986469 (The Pile)

Max Activating Token Index: 1018

Text #18

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0186. Min Act: -0.0000

Data Index: 118053 (The Pile)

Max Activating Token Index: 1019

Text #19

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0185. Min Act: -0.0000

Data Index: 885499 (The Pile)

Max Activating Token Index: 1020