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

Dataset: The Pile

Neuron 3059 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: 0.5572. Min Range: -0.5572

Max Act: 0.5572. Min Act: -0.0000

Data Index: 876758 (The Pile)

Max Activating Token Index: 1020

Text #1

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.5150. Min Act: -0.0000

Data Index: 267024 (The Pile)

Max Activating Token Index: 767

Text #2

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.5151. Min Act: -0.0000

Data Index: 726620 (The Pile)

Max Activating Token Index: 203

Text #3

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.4514. Min Act: -0.0000

Data Index: 1941045 (The Pile)

Max Activating Token Index: 906

Text #4

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.4647. Min Act: -0.0000

Data Index: 172220 (The Pile)

Max Activating Token Index: 940

Text #5

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.4710. Min Act: -0.0000

Data Index: 371818 (The Pile)

Max Activating Token Index: 908

Text #6

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.4845. Min Act: -0.0000

Data Index: 421279 (The Pile)

Max Activating Token Index: 799

Text #7

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1515741 (The Pile)

Max Activating Token Index: 970

Text #8

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.4637. Min Act: -0.0000

Data Index: 1345849 (The Pile)

Max Activating Token Index: 421

Text #9

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.4533. Min Act: -0.0000

Data Index: 1691281 (The Pile)

Max Activating Token Index: 820

Text #10

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.4608. Min Act: -0.0000

Data Index: 1057376 (The Pile)

Max Activating Token Index: 814

Text #11

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.4577. Min Act: -0.0000

Data Index: 498150 (The Pile)

Max Activating Token Index: 873

Text #12

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.4118. Min Act: -0.0000

Data Index: 490563 (The Pile)

Max Activating Token Index: 952

Text #13

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.4354. Min Act: -0.0000

Data Index: 1462605 (The Pile)

Max Activating Token Index: 621

Text #14

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.4328. Min Act: -0.0000

Data Index: 905717 (The Pile)

Max Activating Token Index: 537

Text #15

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.4015. Min Act: -0.0000

Data Index: 1526386 (The Pile)

Max Activating Token Index: 575

Text #16

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.4314. Min Act: -0.0000

Data Index: 813384 (The Pile)

Max Activating Token Index: 424

Text #17

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.4156. Min Act: -0.0000

Data Index: 1439239 (The Pile)

Max Activating Token Index: 914

Text #18

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.4272. Min Act: -0.0000

Data Index: 865245 (The Pile)

Max Activating Token Index: 725

Text #19

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.4421. Min Act: -0.0000

Data Index: 1574477 (The Pile)

Max Activating Token Index: 206