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

Dataset: The Pile

Neuron 3849 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.5085. Min Act: -0.0000

Data Index: 1701294 (The Pile)

Max Activating Token Index: 389

Text #1

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1707112 (The Pile)

Max Activating Token Index: 544

Text #2

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1688853 (The Pile)

Max Activating Token Index: 432

Text #3

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4456. Min Act: -0.0000

Data Index: 542554 (The Pile)

Max Activating Token Index: 426

Text #4

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4285. Min Act: -0.0000

Data Index: 225836 (The Pile)

Max Activating Token Index: 107

Text #5

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4225. Min Act: -0.0000

Data Index: 607248 (The Pile)

Max Activating Token Index: 661

Text #6

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4102. Min Act: -0.0000

Data Index: 1255063 (The Pile)

Max Activating Token Index: 496

Text #7

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3858. Min Act: -0.0000

Data Index: 719589 (The Pile)

Max Activating Token Index: 414

Text #8

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3823. Min Act: -0.0000

Data Index: 1956571 (The Pile)

Max Activating Token Index: 1019

Text #9

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3762. Min Act: -0.0000

Data Index: 1764439 (The Pile)

Max Activating Token Index: 182

Text #10

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3879. Min Act: -0.0000

Data Index: 1116921 (The Pile)

Max Activating Token Index: 571

Text #11

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4014. Min Act: -0.0000

Data Index: 1536496 (The Pile)

Max Activating Token Index: 395

Text #12

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1658131 (The Pile)

Max Activating Token Index: 862

Text #13

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3725. Min Act: -0.0000

Data Index: 1889727 (The Pile)

Max Activating Token Index: 120

Text #14

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3721. Min Act: -0.0000

Data Index: 1811862 (The Pile)

Max Activating Token Index: 359

Text #15

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3610. Min Act: -0.0000

Data Index: 418779 (The Pile)

Max Activating Token Index: 165

Text #16

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3853. Min Act: -0.0000

Data Index: 1888435 (The Pile)

Max Activating Token Index: 937

Text #17

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1818819 (The Pile)

Max Activating Token Index: 618

Text #18

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3583. Min Act: -0.0000

Data Index: 1613715 (The Pile)

Max Activating Token Index: 277

Text #19

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3465. Min Act: -0.0000

Data Index: 1263734 (The Pile)

Max Activating Token Index: 655