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

Dataset: The Pile

Neuron 4190 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: 3.1391. Min Range: -3.1391

Max Act: 3.1391. Min Act: -0.0000

Data Index: 1847299 (The Pile)

Max Activating Token Index: 883

Text #1

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.0550. Min Act: -0.0000

Data Index: 1576147 (The Pile)

Max Activating Token Index: 586

Text #2

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.1172. Min Act: -0.0000

Data Index: 390199 (The Pile)

Max Activating Token Index: 470

Text #3

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.1076. Min Act: -0.0000

Data Index: 1155356 (The Pile)

Max Activating Token Index: 984

Text #4

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.0695. Min Act: -0.0000

Data Index: 938346 (The Pile)

Max Activating Token Index: 803

Text #5

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.0645. Min Act: -0.0000

Data Index: 437108 (The Pile)

Max Activating Token Index: 981

Text #6

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.1321. Min Act: -0.0000

Data Index: 1380324 (The Pile)

Max Activating Token Index: 748

Text #7

Max Range: 3.1391. Min Range: -3.1391

Max Act: 1.9062. Min Act: -0.0000

Data Index: 1089302 (The Pile)

Max Activating Token Index: 603

Text #8

Max Range: 3.1391. Min Range: -3.1391

Max Act: 1.9945. Min Act: -0.0000

Data Index: 1749068 (The Pile)

Max Activating Token Index: 1022

Text #9

Max Range: 3.1391. Min Range: -3.1391

Max Act: 1.9533. Min Act: -0.0000

Data Index: 1167720 (The Pile)

Max Activating Token Index: 752

Text #10

Max Range: 3.1391. Min Range: -3.1391

Max Act: 1.8545. Min Act: -0.0000

Data Index: 604755 (The Pile)

Max Activating Token Index: 308

Text #11

Max Range: 3.1391. Min Range: -3.1391

Max Act: 1.9512. Min Act: -0.0000

Data Index: 426583 (The Pile)

Max Activating Token Index: 829

Text #12

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.0186. Min Act: -0.0000

Data Index: 1657964 (The Pile)

Max Activating Token Index: 854

Text #13

Max Range: 3.1391. Min Range: -3.1391

Max Act: 1.8997. Min Act: -0.0000

Data Index: 1476612 (The Pile)

Max Activating Token Index: 501

Text #14

Max Range: 3.1391. Min Range: -3.1391

Max Act: 1.9175. Min Act: -0.0000

Data Index: 92933 (The Pile)

Max Activating Token Index: 791

Text #15

Max Range: 3.1391. Min Range: -3.1391

Max Act: 1.9166. Min Act: -0.0000

Data Index: 160550 (The Pile)

Max Activating Token Index: 635

Text #16

Max Range: 3.1391. Min Range: -3.1391

Max Act: 1.8037. Min Act: -0.0000

Data Index: 1964827 (The Pile)

Max Activating Token Index: 5

Text #17

Max Range: 3.1391. Min Range: -3.1391

Max Act: 1.7703. Min Act: -0.0000

Data Index: 530114 (The Pile)

Max Activating Token Index: 917

Text #18

Max Range: 3.1391. Min Range: -3.1391

Max Act: 1.8438. Min Act: -0.0000

Data Index: 1137421 (The Pile)

Max Activating Token Index: 743

Text #19

Max Range: 3.1391. Min Range: -3.1391

Max Act: 1.8447. Min Act: -0.0000

Data Index: 1038142 (The Pile)

Max Activating Token Index: 490