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

Dataset: The Pile

Neuron 310 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: 0.5931. Min Range: -0.5931

Max Act: 0.5931. Min Act: -0.0000

Data Index: 1712503 (The Pile)

Max Activating Token Index: 690

Text #1

Max Range: 0.5931. Min Range: -0.5931

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1465959 (The Pile)

Max Activating Token Index: 424

Text #2

Max Range: 0.5931. Min Range: -0.5931

Max Act: 0.5269. Min Act: 0.0000

Data Index: 1881994 (The Pile)

Max Activating Token Index: 148

Text #3

Max Range: 0.5931. Min Range: -0.5931

Max Act: 0.5263. Min Act: -0.0000

Data Index: 309059 (The Pile)

Max Activating Token Index: 585

Text #4

Max Range: 0.5931. Min Range: -0.5931

Max Act: 0.5187. Min Act: -0.0000

Data Index: 517218 (The Pile)

Max Activating Token Index: 743

Text #5

Max Range: 0.5931. Min Range: -0.5931

Max Act: 0.4557. Min Act: -0.0000

Data Index: 400667 (The Pile)

Max Activating Token Index: 762

Text #6

Max Range: 0.5931. Min Range: -0.5931

Max Act: 0.4661. Min Act: -0.0000

Data Index: 932679 (The Pile)

Max Activating Token Index: 237

Text #7

Max Range: 0.5931. Min Range: -0.5931

Max Act: 0.4383. Min Act: -0.0000

Data Index: 1681790 (The Pile)

Max Activating Token Index: 851

Text #8

Max Range: 0.5931. Min Range: -0.5931

Max Act: 0.4468. Min Act: -0.0000

Data Index: 1033974 (The Pile)

Max Activating Token Index: 40

Text #9

Max Range: 0.5931. Min Range: -0.5931

Max Act: 0.4643. Min Act: 0.0000

Data Index: 1001661 (The Pile)

Max Activating Token Index: 730

Text #10

Max Range: 0.5931. Min Range: -0.5931

Max Act: 0.4464. Min Act: -0.0000

Data Index: 93614 (The Pile)

Max Activating Token Index: 521

Text #11

Max Range: 0.5931. Min Range: -0.5931

Max Act: 0.4270. Min Act: -0.0000

Data Index: 1333501 (The Pile)

Max Activating Token Index: 892

Text #12

Max Range: 0.5931. Min Range: -0.5931

Max Act: 0.4117. Min Act: 0.0000

Data Index: 953868 (The Pile)

Max Activating Token Index: 935

Text #13

Max Range: 0.5931. Min Range: -0.5931

Max Act: 0.4105. Min Act: 0.0001

Data Index: 1853107 (The Pile)

Max Activating Token Index: 517

Text #14

Max Range: 0.5931. Min Range: -0.5931

Max Act: 0.4226. Min Act: -0.0000

Data Index: 105281 (The Pile)

Max Activating Token Index: 680

Text #15

Max Range: 0.5931. Min Range: -0.5931

Max Act: 0.3949. Min Act: -0.0000

Data Index: 159482 (The Pile)

Max Activating Token Index: 101

Text #16

Max Range: 0.5931. Min Range: -0.5931

Max Act: 0.4152. Min Act: -0.0000

Data Index: 1363410 (The Pile)

Max Activating Token Index: 719

Text #17

Max Range: 0.5931. Min Range: -0.5931

Max Act: 0.3981. Min Act: -0.0000

Data Index: 1349097 (The Pile)

Max Activating Token Index: 121

Text #18

Max Range: 0.5931. Min Range: -0.5931

Max Act: 0.4075. Min Act: -0.0000

Data Index: 1603036 (The Pile)

Max Activating Token Index: 904

Text #19

Max Range: 0.5931. Min Range: -0.5931

Max Act: 0.4043. Min Act: -0.0000

Data Index: 1168388 (The Pile)

Max Activating Token Index: 37