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

Dataset: The Pile

Neuron 1759 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.4104. Min Act: -0.0000

Data Index: 818597 (The Pile)

Max Activating Token Index: 752

Text #1

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.0162. Min Act: -0.0000

Data Index: 831574 (The Pile)

Max Activating Token Index: 288

Text #2

Max Range: 1.4104. Min Range: -1.4104

Max Act: 0.9923. Min Act: -0.0000

Data Index: 1581766 (The Pile)

Max Activating Token Index: 572

Text #3

Max Range: 1.4104. Min Range: -1.4104

Max Act: 0.9222. Min Act: -0.0000

Data Index: 842871 (The Pile)

Max Activating Token Index: 956

Text #4

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.0199. Min Act: -0.0000

Data Index: 1757848 (The Pile)

Max Activating Token Index: 364

Text #5

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.0039. Min Act: -0.0000

Data Index: 1663153 (The Pile)

Max Activating Token Index: 950

Text #6

Max Range: 1.4104. Min Range: -1.4104

Max Act: 0.9467. Min Act: -0.0000

Data Index: 1032163 (The Pile)

Max Activating Token Index: 989

Text #7

Max Range: 1.4104. Min Range: -1.4104

Max Act: 0.8821. Min Act: -0.0000

Data Index: 861594 (The Pile)

Max Activating Token Index: 362

Text #8

Max Range: 1.4104. Min Range: -1.4104

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1709434 (The Pile)

Max Activating Token Index: 887

Text #9

Max Range: 1.4104. Min Range: -1.4104

Max Act: 0.8905. Min Act: -0.0000

Data Index: 287940 (The Pile)

Max Activating Token Index: 459

Text #10

Max Range: 1.4104. Min Range: -1.4104

Max Act: 0.9780. Min Act: -0.0000

Data Index: 780649 (The Pile)

Max Activating Token Index: 793

Text #11

Max Range: 1.4104. Min Range: -1.4104

Max Act: 0.8370. Min Act: -0.0000

Data Index: 1214100 (The Pile)

Max Activating Token Index: 257

Text #12

Max Range: 1.4104. Min Range: -1.4104

Max Act: 0.8606. Min Act: -0.0000

Data Index: 1435123 (The Pile)

Max Activating Token Index: 61

Text #13

Max Range: 1.4104. Min Range: -1.4104

Max Act: 0.7997. Min Act: -0.0000

Data Index: 120552 (The Pile)

Max Activating Token Index: 603

Text #14

Max Range: 1.4104. Min Range: -1.4104

Max Act: 0.7685. Min Act: -0.0000

Data Index: 1418868 (The Pile)

Max Activating Token Index: 431

Text #15

Max Range: 1.4104. Min Range: -1.4104

Max Act: 0.7662. Min Act: -0.0000

Data Index: 89209 (The Pile)

Max Activating Token Index: 883

Text #16

Max Range: 1.4104. Min Range: -1.4104

Max Act: 0.7655. Min Act: -0.0000

Data Index: 1601949 (The Pile)

Max Activating Token Index: 1003

Text #17

Max Range: 1.4104. Min Range: -1.4104

Max Act: 0.7602. Min Act: -0.0000

Data Index: 206818 (The Pile)

Max Activating Token Index: 387

Text #18

Max Range: 1.4104. Min Range: -1.4104

Max Act: 0.8069. Min Act: -0.0000

Data Index: 1184733 (The Pile)

Max Activating Token Index: 774

Text #19

Max Range: 1.4104. Min Range: -1.4104

Max Act: 0.8238. Min Act: -0.0000

Data Index: 664243 (The Pile)

Max Activating Token Index: 966