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

Dataset: The Pile

Neuron 3982 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: 0.8606. Min Range: -0.8606

Max Act: 0.8606. Min Act: -0.0000

Data Index: 1042184 (The Pile)

Max Activating Token Index: 592

Text #1

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.8175. Min Act: -0.0000

Data Index: 979520 (The Pile)

Max Activating Token Index: 384

Text #2

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.8308. Min Act: -0.0000

Data Index: 137430 (The Pile)

Max Activating Token Index: 154

Text #3

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.7864. Min Act: -0.0000

Data Index: 499167 (The Pile)

Max Activating Token Index: 76

Text #4

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.7470. Min Act: -0.0000

Data Index: 922439 (The Pile)

Max Activating Token Index: 583

Text #5

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.7861. Min Act: 0.0000

Data Index: 1141994 (The Pile)

Max Activating Token Index: 17

Text #6

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.7921. Min Act: -0.0000

Data Index: 458951 (The Pile)

Max Activating Token Index: 864

Text #7

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.7003. Min Act: -0.0000

Data Index: 112142 (The Pile)

Max Activating Token Index: 972

Text #8

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.6469. Min Act: -0.0000

Data Index: 736300 (The Pile)

Max Activating Token Index: 636

Text #9

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.7319. Min Act: -0.0000

Data Index: 1278895 (The Pile)

Max Activating Token Index: 1007

Text #10

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.6671. Min Act: -0.0000

Data Index: 840027 (The Pile)

Max Activating Token Index: 676

Text #11

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.6984. Min Act: -0.0000

Data Index: 1309195 (The Pile)

Max Activating Token Index: 463

Text #12

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.7232. Min Act: -0.0000

Data Index: 781429 (The Pile)

Max Activating Token Index: 96

Text #13

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.7383. Min Act: -0.0000

Data Index: 1285117 (The Pile)

Max Activating Token Index: 661

Text #14

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.7102. Min Act: -0.0000

Data Index: 221848 (The Pile)

Max Activating Token Index: 184

Text #15

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.7085. Min Act: -0.0000

Data Index: 1130233 (The Pile)

Max Activating Token Index: 579

Text #16

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.6457. Min Act: -0.0000

Data Index: 1817962 (The Pile)

Max Activating Token Index: 819

Text #17

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.6579. Min Act: -0.0000

Data Index: 382864 (The Pile)

Max Activating Token Index: 522

Text #18

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.6614. Min Act: -0.0000

Data Index: 546690 (The Pile)

Max Activating Token Index: 124

Text #19

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.6730. Min Act: -0.0000

Data Index: 1995666 (The Pile)

Max Activating Token Index: 792