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

Dataset: The Pile

Neuron 2568 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.4340. Min Act: -0.0000

Data Index: 453018 (The Pile)

Max Activating Token Index: 127

Text #1

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.4080. Min Act: -0.0000

Data Index: 1934107 (The Pile)

Max Activating Token Index: 598

Text #2

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.4004. Min Act: -0.0000

Data Index: 1107238 (The Pile)

Max Activating Token Index: 132

Text #3

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3733. Min Act: -0.0000

Data Index: 1556732 (The Pile)

Max Activating Token Index: 650

Text #4

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3887. Min Act: -0.0000

Data Index: 1188019 (The Pile)

Max Activating Token Index: 85

Text #5

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.2913. Min Act: -0.0000

Data Index: 1137631 (The Pile)

Max Activating Token Index: 764

Text #6

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3586. Min Act: -0.0000

Data Index: 1017077 (The Pile)

Max Activating Token Index: 203

Text #7

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3833. Min Act: -0.0000

Data Index: 1424103 (The Pile)

Max Activating Token Index: 644

Text #8

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3924. Min Act: -0.0000

Data Index: 1924466 (The Pile)

Max Activating Token Index: 384

Text #9

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3254. Min Act: -0.0000

Data Index: 765658 (The Pile)

Max Activating Token Index: 726

Text #10

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3369. Min Act: -0.0000

Data Index: 1592255 (The Pile)

Max Activating Token Index: 468

Text #11

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3178. Min Act: -0.0000

Data Index: 1254398 (The Pile)

Max Activating Token Index: 510

Text #12

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3376. Min Act: -0.0000

Data Index: 363210 (The Pile)

Max Activating Token Index: 561

Text #13

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3158. Min Act: -0.0000

Data Index: 782821 (The Pile)

Max Activating Token Index: 324

Text #14

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3126. Min Act: -0.0000

Data Index: 1706142 (The Pile)

Max Activating Token Index: 845

Text #15

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3242. Min Act: -0.0000

Data Index: 1183817 (The Pile)

Max Activating Token Index: 103

Text #16

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1714349 (The Pile)

Max Activating Token Index: 503

Text #17

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.2835. Min Act: -0.0000

Data Index: 5043 (The Pile)

Max Activating Token Index: 177

Text #18

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3081. Min Act: -0.0000

Data Index: 1057869 (The Pile)

Max Activating Token Index: 251

Text #19

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.2926. Min Act: -0.0000

Data Index: 992074 (The Pile)

Max Activating Token Index: 653