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

Dataset: The Pile

Neuron 2289 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.0722. Min Act: -0.0000

Data Index: 566975 (The Pile)

Max Activating Token Index: 892

Text #1

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.2114. Min Act: -0.0000

Data Index: 1725096 (The Pile)

Max Activating Token Index: 728

Text #2

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1496. Min Act: -0.0000

Data Index: 1137681 (The Pile)

Max Activating Token Index: 657

Text #3

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1536. Min Act: -0.0000

Data Index: 1077600 (The Pile)

Max Activating Token Index: 904

Text #4

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1349. Min Act: -0.0000

Data Index: 280674 (The Pile)

Max Activating Token Index: 879

Text #5

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1235. Min Act: -0.0000

Data Index: 128939 (The Pile)

Max Activating Token Index: 539

Text #6

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1360. Min Act: -0.0000

Data Index: 1035192 (The Pile)

Max Activating Token Index: 631

Text #7

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1149. Min Act: -0.0000

Data Index: 1182686 (The Pile)

Max Activating Token Index: 442

Text #8

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1066. Min Act: -0.0000

Data Index: 295403 (The Pile)

Max Activating Token Index: 27

Text #9

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1224. Min Act: -0.0000

Data Index: 1248001 (The Pile)

Max Activating Token Index: 636

Text #10

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1429. Min Act: -0.0000

Data Index: 11572 (The Pile)

Max Activating Token Index: 762

Text #11

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1165. Min Act: -0.0000

Data Index: 1671316 (The Pile)

Max Activating Token Index: 509

Text #12

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1059. Min Act: -0.0000

Data Index: 1725818 (The Pile)

Max Activating Token Index: 300

Text #13

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1228. Min Act: -0.0000

Data Index: 478193 (The Pile)

Max Activating Token Index: 279

Text #14

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1038. Min Act: -0.0000

Data Index: 1013673 (The Pile)

Max Activating Token Index: 135

Text #15

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1070. Min Act: -0.0000

Data Index: 265208 (The Pile)

Max Activating Token Index: 436

Text #16

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.0923. Min Act: -0.0000

Data Index: 1686867 (The Pile)

Max Activating Token Index: 213

Text #17

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.0958. Min Act: -0.0000

Data Index: 1407021 (The Pile)

Max Activating Token Index: 780

Text #18

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1077. Min Act: -0.0000

Data Index: 487843 (The Pile)

Max Activating Token Index: 806

Text #19

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.0957. Min Act: -0.0000

Data Index: 1884058 (The Pile)

Max Activating Token Index: 181