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

Dataset: The Pile

Neuron 3631 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1599. Min Range: -1.1599

Max Act: 1.1599. Min Act: -0.0000

Data Index: 70813 (The Pile)

Max Activating Token Index: 578

Text #1

Max Range: 1.1599. Min Range: -1.1599

Max Act: 1.0559. Min Act: -0.0000

Data Index: 1287466 (The Pile)

Max Activating Token Index: 141

Text #2

Max Range: 1.1599. Min Range: -1.1599

Max Act: 1.0160. Min Act: -0.0000

Data Index: 1036262 (The Pile)

Max Activating Token Index: 759

Text #3

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.9182. Min Act: -0.0000

Data Index: 949585 (The Pile)

Max Activating Token Index: 105

Text #4

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.9373. Min Act: -0.0000

Data Index: 365545 (The Pile)

Max Activating Token Index: 461

Text #5

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.9114. Min Act: -0.0000

Data Index: 63228 (The Pile)

Max Activating Token Index: 524

Text #6

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8706. Min Act: -0.0000

Data Index: 1026207 (The Pile)

Max Activating Token Index: 144

Text #7

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8842. Min Act: -0.0000

Data Index: 1114760 (The Pile)

Max Activating Token Index: 475

Text #8

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.9063. Min Act: -0.0000

Data Index: 1816523 (The Pile)

Max Activating Token Index: 591

Text #9

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8926. Min Act: -0.0000

Data Index: 226986 (The Pile)

Max Activating Token Index: 243

Text #10

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8451. Min Act: -0.0000

Data Index: 738177 (The Pile)

Max Activating Token Index: 340

Text #11

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8129. Min Act: -0.0000

Data Index: 1914260 (The Pile)

Max Activating Token Index: 1022

Text #12

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8372. Min Act: -0.0000

Data Index: 384304 (The Pile)

Max Activating Token Index: 89

Text #13

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8744. Min Act: -0.0000

Data Index: 1345191 (The Pile)

Max Activating Token Index: 634

Text #14

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.7927. Min Act: -0.0000

Data Index: 1449318 (The Pile)

Max Activating Token Index: 571

Text #15

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8402. Min Act: -0.0000

Data Index: 1264670 (The Pile)

Max Activating Token Index: 884

Text #16

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8323. Min Act: -0.0000

Data Index: 233924 (The Pile)

Max Activating Token Index: 766

Text #17

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8345. Min Act: -0.0000

Data Index: 1055878 (The Pile)

Max Activating Token Index: 694

Text #18

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8335. Min Act: -0.0000

Data Index: 394845 (The Pile)

Max Activating Token Index: 717

Text #19

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8321. Min Act: -0.0000

Data Index: 568875 (The Pile)

Max Activating Token Index: 836