Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3348 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0251. Min Act: -0.0000

Data Index: 1092174 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0240. Min Act: -0.0000

Data Index: 920466 (The Pile)

Max Activating Token Index: 963

Text #2

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0236. Min Act: -0.0000

Data Index: 1519320 (The Pile)

Max Activating Token Index: 947

Text #3

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0231. Min Act: -0.0000

Data Index: 1257110 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0220. Min Act: -0.0000

Data Index: 287873 (The Pile)

Max Activating Token Index: 996

Text #5

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0213. Min Act: -0.0000

Data Index: 1662032 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0213. Min Act: -0.0000

Data Index: 1130156 (The Pile)

Max Activating Token Index: 1002

Text #7

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0207. Min Act: -0.0000

Data Index: 1086256 (The Pile)

Max Activating Token Index: 997

Text #8

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0205. Min Act: -0.0000

Data Index: 1246867 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0204. Min Act: -0.0000

Data Index: 1804429 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0203. Min Act: -0.0000

Data Index: 50233 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0201. Min Act: -0.0000

Data Index: 1887781 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0199. Min Act: -0.0000

Data Index: 1929573 (The Pile)

Max Activating Token Index: 1011

Text #13

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0194. Min Act: -0.0001

Data Index: 953803 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0193. Min Act: -0.0000

Data Index: 324779 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0191. Min Act: -0.0000

Data Index: 1131715 (The Pile)

Max Activating Token Index: 1015

Text #16

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0190. Min Act: -0.0000

Data Index: 1842141 (The Pile)

Max Activating Token Index: 856

Text #17

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0185. Min Act: -0.0000

Data Index: 1032544 (The Pile)

Max Activating Token Index: 849

Text #18

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0190. Min Act: -0.0000

Data Index: 368481 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0190. Min Act: -0.0000

Data Index: 50417 (The Pile)

Max Activating Token Index: 1018