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

Dataset: The Pile

Neuron 5017 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3048. Min Range: -1.3048

Max Act: 1.1314. Min Act: -0.0000

Data Index: 1882867 (The Pile)

Max Activating Token Index: 76

Text #1

Max Range: 1.3048. Min Range: -1.3048

Max Act: 1.1964. Min Act: -0.0000

Data Index: 889934 (The Pile)

Max Activating Token Index: 41

Text #2

Max Range: 1.3048. Min Range: -1.3048

Max Act: 1.1998. Min Act: -0.0000

Data Index: 524833 (The Pile)

Max Activating Token Index: 44

Text #3

Max Range: 1.3048. Min Range: -1.3048

Max Act: 1.2448. Min Act: -0.0000

Data Index: 1780018 (The Pile)

Max Activating Token Index: 49

Text #4

Max Range: 1.3048. Min Range: -1.3048

Max Act: 1.1688. Min Act: -0.0000

Data Index: 175588 (The Pile)

Max Activating Token Index: 83

Text #5

Max Range: 1.3048. Min Range: -1.3048

Max Act: 1.3048. Min Act: -0.0000

Data Index: 1477342 (The Pile)

Max Activating Token Index: 76

Text #6

Max Range: 1.3048. Min Range: -1.3048

Max Act: 1.0362. Min Act: -0.0000

Data Index: 1449496 (The Pile)

Max Activating Token Index: 121

Text #7

Max Range: 1.3048. Min Range: -1.3048

Max Act: 1.0123. Min Act: -0.0000

Data Index: 1342975 (The Pile)

Max Activating Token Index: 96

Text #8

Max Range: 1.3048. Min Range: -1.3048

Max Act: 1.0579. Min Act: -0.0000

Data Index: 1129956 (The Pile)

Max Activating Token Index: 77

Text #9

Max Range: 1.3048. Min Range: -1.3048

Max Act: 1.1764. Min Act: -0.0000

Data Index: 979606 (The Pile)

Max Activating Token Index: 58

Text #10

Max Range: 1.3048. Min Range: -1.3048

Max Act: 1.1562. Min Act: -0.0000

Data Index: 1344576 (The Pile)

Max Activating Token Index: 34

Text #11

Max Range: 1.3048. Min Range: -1.3048

Max Act: 1.1650. Min Act: -0.0000

Data Index: 707397 (The Pile)

Max Activating Token Index: 120

Text #12

Max Range: 1.3048. Min Range: -1.3048

Max Act: 1.0188. Min Act: -0.0000

Data Index: 603713 (The Pile)

Max Activating Token Index: 564

Text #13

Max Range: 1.3048. Min Range: -1.3048

Max Act: 0.9750. Min Act: -0.0000

Data Index: 1663687 (The Pile)

Max Activating Token Index: 172

Text #14

Max Range: 1.3048. Min Range: -1.3048

Max Act: 1.1443. Min Act: -0.0000

Data Index: 595712 (The Pile)

Max Activating Token Index: 107

Text #15

Max Range: 1.3048. Min Range: -1.3048

Max Act: 1.0044. Min Act: -0.0000

Data Index: 1354345 (The Pile)

Max Activating Token Index: 54

Text #16

Max Range: 1.3048. Min Range: -1.3048

Max Act: 0.9975. Min Act: -0.0000

Data Index: 1984197 (The Pile)

Max Activating Token Index: 100

Text #17

Max Range: 1.3048. Min Range: -1.3048

Max Act: 0.9989. Min Act: -0.0000

Data Index: 333883 (The Pile)

Max Activating Token Index: 153

Text #18

Max Range: 1.3048. Min Range: -1.3048

Max Act: 1.0231. Min Act: -0.0000

Data Index: 572985 (The Pile)

Max Activating Token Index: 103

Text #19

Max Range: 1.3048. Min Range: -1.3048

Max Act: 1.0932. Min Act: -0.0000

Data Index: 339713 (The Pile)

Max Activating Token Index: 123