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

Dataset: The Pile

Neuron 928 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: 0.3260. Min Range: -0.3260

Max Act: 0.3119. Min Act: -0.0000

Data Index: 674676 (The Pile)

Max Activating Token Index: 961

Text #1

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.3260. Min Act: -0.0000

Data Index: 1165331 (The Pile)

Max Activating Token Index: 397

Text #2

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.3024. Min Act: -0.0000

Data Index: 943236 (The Pile)

Max Activating Token Index: 710

Text #3

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.2852. Min Act: -0.0000

Data Index: 1702939 (The Pile)

Max Activating Token Index: 969

Text #4

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.2870. Min Act: -0.0000

Data Index: 1260210 (The Pile)

Max Activating Token Index: 602

Text #5

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.2899. Min Act: -0.0000

Data Index: 1618200 (The Pile)

Max Activating Token Index: 144

Text #6

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.2919. Min Act: -0.0000

Data Index: 39458 (The Pile)

Max Activating Token Index: 173

Text #7

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.2647. Min Act: -0.0000

Data Index: 571987 (The Pile)

Max Activating Token Index: 868

Text #8

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.2753. Min Act: -0.0000

Data Index: 1503157 (The Pile)

Max Activating Token Index: 938

Text #9

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.2435. Min Act: -0.0000

Data Index: 1753999 (The Pile)

Max Activating Token Index: 518

Text #10

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.2397. Min Act: -0.0000

Data Index: 1918367 (The Pile)

Max Activating Token Index: 916

Text #11

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.2456. Min Act: -0.0000

Data Index: 1376495 (The Pile)

Max Activating Token Index: 157

Text #12

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.2435. Min Act: -0.0000

Data Index: 1818116 (The Pile)

Max Activating Token Index: 110

Text #13

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.2519. Min Act: -0.0000

Data Index: 405597 (The Pile)

Max Activating Token Index: 96

Text #14

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.2438. Min Act: -0.0000

Data Index: 1452726 (The Pile)

Max Activating Token Index: 931

Text #15

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.2576. Min Act: -0.0000

Data Index: 28144 (The Pile)

Max Activating Token Index: 109

Text #16

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.2484. Min Act: -0.0000

Data Index: 1406621 (The Pile)

Max Activating Token Index: 641

Text #17

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.2527. Min Act: -0.0000

Data Index: 268919 (The Pile)

Max Activating Token Index: 112

Text #18

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.2452. Min Act: -0.0000

Data Index: 821967 (The Pile)

Max Activating Token Index: 748

Text #19

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.2577. Min Act: -0.0000

Data Index: 615652 (The Pile)

Max Activating Token Index: 424