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

Dataset: The Pile

Neuron 3833 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: 0.0249. Min Range: -0.0249

Max Act: 0.0249. Min Act: -0.0000

Data Index: 605116 (The Pile)

Max Activating Token Index: 988

Text #1

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0246. Min Act: -0.0000

Data Index: 280929 (The Pile)

Max Activating Token Index: 1008

Text #2

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0244. Min Act: -0.0000

Data Index: 1273220 (The Pile)

Max Activating Token Index: 1016

Text #3

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0244. Min Act: -0.0000

Data Index: 1833198 (The Pile)

Max Activating Token Index: 1005

Text #4

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0232. Min Act: -0.0000

Data Index: 976727 (The Pile)

Max Activating Token Index: 980

Text #5

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0239. Min Act: -0.0000

Data Index: 328019 (The Pile)

Max Activating Token Index: 1014

Text #6

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0228. Min Act: -0.0000

Data Index: 1582714 (The Pile)

Max Activating Token Index: 935

Text #7

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0227. Min Act: -0.0000

Data Index: 338074 (The Pile)

Max Activating Token Index: 948

Text #8

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0224. Min Act: -0.0000

Data Index: 1299787 (The Pile)

Max Activating Token Index: 971

Text #9

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0232. Min Act: -0.0000

Data Index: 890396 (The Pile)

Max Activating Token Index: 1011

Text #10

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0218. Min Act: -0.0000

Data Index: 1065743 (The Pile)

Max Activating Token Index: 985

Text #11

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0218. Min Act: -0.0000

Data Index: 421341 (The Pile)

Max Activating Token Index: 984

Text #12

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0218. Min Act: -0.0000

Data Index: 1168461 (The Pile)

Max Activating Token Index: 959

Text #13

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0217. Min Act: -0.0000

Data Index: 613166 (The Pile)

Max Activating Token Index: 978

Text #14

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0217. Min Act: -0.0000

Data Index: 928834 (The Pile)

Max Activating Token Index: 962

Text #15

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0214. Min Act: -0.0000

Data Index: 37380 (The Pile)

Max Activating Token Index: 990

Text #16

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0213. Min Act: -0.0000

Data Index: 635331 (The Pile)

Max Activating Token Index: 978

Text #17

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0213. Min Act: -0.0000

Data Index: 1131846 (The Pile)

Max Activating Token Index: 892

Text #18

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0213. Min Act: -0.0000

Data Index: 1356877 (The Pile)

Max Activating Token Index: 1016

Text #19

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0211. Min Act: -0.0000

Data Index: 663591 (The Pile)

Max Activating Token Index: 997