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

Dataset: The Pile

Neuron 1946 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3036. Min Range: -3.3036

Max Act: 3.3036. Min Act: -0.0000

Data Index: 876256 (The Pile)

Max Activating Token Index: 353

Text #1

Max Range: 3.3036. Min Range: -3.3036

Max Act: 2.3189. Min Act: -0.0000

Data Index: 1311580 (The Pile)

Max Activating Token Index: 869

Text #2

Max Range: 3.3036. Min Range: -3.3036

Max Act: 2.0408. Min Act: -0.0000

Data Index: 917800 (The Pile)

Max Activating Token Index: 197

Text #3

Max Range: 3.3036. Min Range: -3.3036

Max Act: 1.8351. Min Act: -0.0000

Data Index: 1932262 (The Pile)

Max Activating Token Index: 905

Text #4

Max Range: 3.3036. Min Range: -3.3036

Max Act: 1.8890. Min Act: -0.0000

Data Index: 293693 (The Pile)

Max Activating Token Index: 577

Text #5

Max Range: 3.3036. Min Range: -3.3036

Max Act: 1.8373. Min Act: -0.0000

Data Index: 1122949 (The Pile)

Max Activating Token Index: 274

Text #6

Max Range: 3.3036. Min Range: -3.3036

Max Act: 1.8086. Min Act: -0.0000

Data Index: 999296 (The Pile)

Max Activating Token Index: 647

Text #7

Max Range: 3.3036. Min Range: -3.3036

Max Act: 1.7668. Min Act: -0.0000

Data Index: 1935859 (The Pile)

Max Activating Token Index: 586

Text #8

Max Range: 3.3036. Min Range: -3.3036

Max Act: 1.7228. Min Act: -0.0000

Data Index: 129763 (The Pile)

Max Activating Token Index: 380

Text #9

Max Range: 3.3036. Min Range: -3.3036

Max Act: 1.8424. Min Act: -0.0000

Data Index: 1134720 (The Pile)

Max Activating Token Index: 941

Text #10

Max Range: 3.3036. Min Range: -3.3036

Max Act: 1.6813. Min Act: -0.0000

Data Index: 1008360 (The Pile)

Max Activating Token Index: 354

Text #11

Max Range: 3.3036. Min Range: -3.3036

Max Act: 1.4704. Min Act: -0.0000

Data Index: 272406 (The Pile)

Max Activating Token Index: 502

Text #12

Max Range: 3.3036. Min Range: -3.3036

Max Act: 1.5654. Min Act: -0.0000

Data Index: 1727471 (The Pile)

Max Activating Token Index: 598

Text #13

Max Range: 3.3036. Min Range: -3.3036

Max Act: 1.5560. Min Act: -0.0000

Data Index: 937644 (The Pile)

Max Activating Token Index: 170

Text #14

Max Range: 3.3036. Min Range: -3.3036

Max Act: 1.5973. Min Act: -0.0000

Data Index: 1651138 (The Pile)

Max Activating Token Index: 721

Text #15

Max Range: 3.3036. Min Range: -3.3036

Max Act: 1.4911. Min Act: -0.0000

Data Index: 1334987 (The Pile)

Max Activating Token Index: 105

Text #16

Max Range: 3.3036. Min Range: -3.3036

Max Act: 1.6119. Min Act: -0.0000

Data Index: 587424 (The Pile)

Max Activating Token Index: 163

Text #17

Max Range: 3.3036. Min Range: -3.3036

Max Act: 1.4611. Min Act: -0.0000

Data Index: 229797 (The Pile)

Max Activating Token Index: 193

Text #18

Max Range: 3.3036. Min Range: -3.3036

Max Act: 1.5224. Min Act: -0.0000

Data Index: 1067329 (The Pile)

Max Activating Token Index: 1011

Text #19

Max Range: 3.3036. Min Range: -3.3036

Max Act: 1.4299. Min Act: -0.0000

Data Index: 1633513 (The Pile)

Max Activating Token Index: 272