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

Dataset: The Pile

Neuron 2410 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.7588. Min Act: -0.0000

Data Index: 132769 (The Pile)

Max Activating Token Index: 638

Text #1

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.6739. Min Act: -0.0000

Data Index: 1370147 (The Pile)

Max Activating Token Index: 34

Text #2

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5908. Min Act: 0.0000

Data Index: 1692565 (The Pile)

Max Activating Token Index: 500

Text #3

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5412. Min Act: -0.0000

Data Index: 210698 (The Pile)

Max Activating Token Index: 649

Text #4

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5923. Min Act: -0.0000

Data Index: 362638 (The Pile)

Max Activating Token Index: 878

Text #5

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5770. Min Act: -0.0000

Data Index: 191553 (The Pile)

Max Activating Token Index: 363

Text #6

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.6325. Min Act: -0.0000

Data Index: 1214798 (The Pile)

Max Activating Token Index: 898

Text #7

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5507. Min Act: -0.0000

Data Index: 1579746 (The Pile)

Max Activating Token Index: 206

Text #8

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5090. Min Act: -0.0000

Data Index: 1009658 (The Pile)

Max Activating Token Index: 93

Text #9

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4628. Min Act: -0.0000

Data Index: 760254 (The Pile)

Max Activating Token Index: 339

Text #10

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5253. Min Act: -0.0000

Data Index: 96879 (The Pile)

Max Activating Token Index: 116

Text #11

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1312990 (The Pile)

Max Activating Token Index: 133

Text #12

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1128903 (The Pile)

Max Activating Token Index: 438

Text #13

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4514. Min Act: -0.0000

Data Index: 1393395 (The Pile)

Max Activating Token Index: 237

Text #14

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4699. Min Act: -0.0000

Data Index: 1881178 (The Pile)

Max Activating Token Index: 25

Text #15

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4380. Min Act: -0.0000

Data Index: 973116 (The Pile)

Max Activating Token Index: 871

Text #16

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5053. Min Act: -0.0000

Data Index: 1718196 (The Pile)

Max Activating Token Index: 590

Text #17

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4572. Min Act: -0.0000

Data Index: 38388 (The Pile)

Max Activating Token Index: 749

Text #18

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5133. Min Act: -0.0000

Data Index: 1504575 (The Pile)

Max Activating Token Index: 616

Text #19

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4120. Min Act: -0.0000

Data Index: 761168 (The Pile)

Max Activating Token Index: 158