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

Dataset: The Pile

Neuron 3108 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: 0.9059. Min Range: -0.9059

Max Act: 0.9059. Min Act: -0.0000

Data Index: 1345674 (The Pile)

Max Activating Token Index: 538

Text #1

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8292. Min Act: -0.0000

Data Index: 1070365 (The Pile)

Max Activating Token Index: 231

Text #2

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8089. Min Act: -0.0000

Data Index: 46504 (The Pile)

Max Activating Token Index: 36

Text #3

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.7252. Min Act: -0.0000

Data Index: 739237 (The Pile)

Max Activating Token Index: 717

Text #4

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.7054. Min Act: -0.0000

Data Index: 1168386 (The Pile)

Max Activating Token Index: 903

Text #5

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6989. Min Act: -0.0000

Data Index: 195259 (The Pile)

Max Activating Token Index: 944

Text #6

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.7723. Min Act: -0.0000

Data Index: 1936286 (The Pile)

Max Activating Token Index: 530

Text #7

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.7150. Min Act: -0.0000

Data Index: 464454 (The Pile)

Max Activating Token Index: 329

Text #8

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6536. Min Act: -0.0000

Data Index: 857916 (The Pile)

Max Activating Token Index: 708

Text #9

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6741. Min Act: -0.0000

Data Index: 954011 (The Pile)

Max Activating Token Index: 865

Text #10

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6596. Min Act: -0.0000

Data Index: 1853827 (The Pile)

Max Activating Token Index: 34

Text #11

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.7086. Min Act: -0.0000

Data Index: 516236 (The Pile)

Max Activating Token Index: 638

Text #12

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6594. Min Act: -0.0000

Data Index: 1478999 (The Pile)

Max Activating Token Index: 90

Text #13

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1632280 (The Pile)

Max Activating Token Index: 937

Text #14

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6783. Min Act: -0.0000

Data Index: 1255831 (The Pile)

Max Activating Token Index: 799

Text #15

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.7042. Min Act: -0.0000

Data Index: 244941 (The Pile)

Max Activating Token Index: 74

Text #16

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6366. Min Act: -0.0000

Data Index: 726624 (The Pile)

Max Activating Token Index: 602

Text #17

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6082. Min Act: -0.0000

Data Index: 1706910 (The Pile)

Max Activating Token Index: 969

Text #18

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6621. Min Act: -0.0000

Data Index: 1716734 (The Pile)

Max Activating Token Index: 679

Text #19

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6329. Min Act: -0.0000

Data Index: 1043771 (The Pile)

Max Activating Token Index: 84