Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2944 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5548. Min Act: -0.0000

Data Index: 712400 (The Pile)

Max Activating Token Index: 19

Text #1

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5166. Min Act: -0.0000

Data Index: 1656063 (The Pile)

Max Activating Token Index: 260

Text #2

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1231372 (The Pile)

Max Activating Token Index: 621

Text #3

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5089. Min Act: 0.0000

Data Index: 787552 (The Pile)

Max Activating Token Index: 228

Text #4

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1040975 (The Pile)

Max Activating Token Index: 745

Text #5

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4834. Min Act: -0.0000

Data Index: 1411622 (The Pile)

Max Activating Token Index: 389

Text #6

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1072986 (The Pile)

Max Activating Token Index: 619

Text #7

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4912. Min Act: -0.0000

Data Index: 912480 (The Pile)

Max Activating Token Index: 235

Text #8

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4296. Min Act: -0.0000

Data Index: 1073965 (The Pile)

Max Activating Token Index: 763

Text #9

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4410. Min Act: 0.0000

Data Index: 933635 (The Pile)

Max Activating Token Index: 159

Text #10

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4093. Min Act: 0.0000

Data Index: 963269 (The Pile)

Max Activating Token Index: 828

Text #11

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4462. Min Act: 0.0000

Data Index: 151772 (The Pile)

Max Activating Token Index: 246

Text #12

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1509384 (The Pile)

Max Activating Token Index: 427

Text #13

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4344. Min Act: 0.0000

Data Index: 721746 (The Pile)

Max Activating Token Index: 912

Text #14

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4508. Min Act: -0.0000

Data Index: 1003928 (The Pile)

Max Activating Token Index: 653

Text #15

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4301. Min Act: 0.0000

Data Index: 1441889 (The Pile)

Max Activating Token Index: 1000

Text #16

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1373296 (The Pile)

Max Activating Token Index: 216

Text #17

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4182. Min Act: -0.0000

Data Index: 185656 (The Pile)

Max Activating Token Index: 442

Text #18

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.3980. Min Act: 0.0000

Data Index: 637148 (The Pile)

Max Activating Token Index: 477

Text #19

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.3843. Min Act: -0.0000

Data Index: 401863 (The Pile)

Max Activating Token Index: 500