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

Dataset: The Pile

Neuron 940 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: 0.7239. Min Range: -0.7239

Max Act: 0.7239. Min Act: -0.0000

Data Index: 720734 (The Pile)

Max Activating Token Index: 578

Text #1

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.6852. Min Act: -0.0000

Data Index: 1980654 (The Pile)

Max Activating Token Index: 121

Text #2

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.6859. Min Act: -0.0000

Data Index: 1711736 (The Pile)

Max Activating Token Index: 44

Text #3

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.6563. Min Act: -0.0000

Data Index: 1121601 (The Pile)

Max Activating Token Index: 542

Text #4

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.6622. Min Act: -0.0000

Data Index: 1550531 (The Pile)

Max Activating Token Index: 840

Text #5

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.6912. Min Act: -0.0000

Data Index: 125370 (The Pile)

Max Activating Token Index: 244

Text #6

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.6525. Min Act: -0.0000

Data Index: 1943072 (The Pile)

Max Activating Token Index: 237

Text #7

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.6209. Min Act: 0.0000

Data Index: 1622843 (The Pile)

Max Activating Token Index: 162

Text #8

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.6229. Min Act: 0.0000

Data Index: 1221957 (The Pile)

Max Activating Token Index: 743

Text #9

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.6082. Min Act: -0.0000

Data Index: 594891 (The Pile)

Max Activating Token Index: 258

Text #10

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1761566 (The Pile)

Max Activating Token Index: 865

Text #11

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1677963 (The Pile)

Max Activating Token Index: 140

Text #12

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.5587. Min Act: -0.0000

Data Index: 820915 (The Pile)

Max Activating Token Index: 94

Text #13

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.5874. Min Act: 0.0000

Data Index: 1984557 (The Pile)

Max Activating Token Index: 213

Text #14

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.5674. Min Act: 0.0000

Data Index: 1585990 (The Pile)

Max Activating Token Index: 501

Text #15

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.5433. Min Act: -0.0000

Data Index: 1905513 (The Pile)

Max Activating Token Index: 500

Text #16

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.5586. Min Act: -0.0000

Data Index: 1155557 (The Pile)

Max Activating Token Index: 213

Text #17

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.5338. Min Act: 0.0000

Data Index: 1082104 (The Pile)

Max Activating Token Index: 101

Text #18

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.5745. Min Act: -0.0000

Data Index: 908411 (The Pile)

Max Activating Token Index: 947

Text #19

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.5376. Min Act: -0.0000

Data Index: 1788581 (The Pile)

Max Activating Token Index: 562