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

Dataset: The Pile

Neuron 2474 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.6983. Min Act: -0.0000

Data Index: 1130625 (The Pile)

Max Activating Token Index: 281

Text #1

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.7022. Min Act: -0.0000

Data Index: 92088 (The Pile)

Max Activating Token Index: 40

Text #2

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.7205. Min Act: -0.0000

Data Index: 1337237 (The Pile)

Max Activating Token Index: 342

Text #3

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.6997. Min Act: -0.0000

Data Index: 1913343 (The Pile)

Max Activating Token Index: 408

Text #4

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.6799. Min Act: -0.0000

Data Index: 606807 (The Pile)

Max Activating Token Index: 971

Text #5

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.6021. Min Act: -0.0000

Data Index: 1382920 (The Pile)

Max Activating Token Index: 688

Text #6

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.6339. Min Act: -0.0000

Data Index: 751721 (The Pile)

Max Activating Token Index: 960

Text #7

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.6446. Min Act: -0.0000

Data Index: 1363959 (The Pile)

Max Activating Token Index: 89

Text #8

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5768. Min Act: 0.0001

Data Index: 576652 (The Pile)

Max Activating Token Index: 998

Text #9

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.6786. Min Act: -0.0000

Data Index: 352605 (The Pile)

Max Activating Token Index: 929

Text #10

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.6005. Min Act: -0.0000

Data Index: 1137554 (The Pile)

Max Activating Token Index: 156

Text #11

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.6038. Min Act: -0.0000

Data Index: 826013 (The Pile)

Max Activating Token Index: 379

Text #12

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.6295. Min Act: 0.0000

Data Index: 233545 (The Pile)

Max Activating Token Index: 40

Text #13

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.6027. Min Act: -0.0000

Data Index: 1797519 (The Pile)

Max Activating Token Index: 501

Text #14

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5871. Min Act: -0.0000

Data Index: 1776268 (The Pile)

Max Activating Token Index: 291

Text #15

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5884. Min Act: -0.0000

Data Index: 1911053 (The Pile)

Max Activating Token Index: 184

Text #16

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5970. Min Act: 0.0000

Data Index: 633893 (The Pile)

Max Activating Token Index: 862

Text #17

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5589. Min Act: -0.0000

Data Index: 45568 (The Pile)

Max Activating Token Index: 173

Text #18

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5405. Min Act: -0.0000

Data Index: 1790251 (The Pile)

Max Activating Token Index: 741

Text #19

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5727. Min Act: -0.0000

Data Index: 367713 (The Pile)

Max Activating Token Index: 1001