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

Dataset: The Pile

Neuron 952 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5752. Min Range: -1.5752

Max Act: 1.5752. Min Act: -0.0000

Data Index: 465563 (The Pile)

Max Activating Token Index: 88

Text #1

Max Range: 1.5752. Min Range: -1.5752

Max Act: 1.2715. Min Act: -0.0000

Data Index: 1583806 (The Pile)

Max Activating Token Index: 191

Text #2

Max Range: 1.5752. Min Range: -1.5752

Max Act: 1.0841. Min Act: -0.0000

Data Index: 1580016 (The Pile)

Max Activating Token Index: 925

Text #3

Max Range: 1.5752. Min Range: -1.5752

Max Act: 1.1001. Min Act: -0.0000

Data Index: 93192 (The Pile)

Max Activating Token Index: 224

Text #4

Max Range: 1.5752. Min Range: -1.5752

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1618071 (The Pile)

Max Activating Token Index: 675

Text #5

Max Range: 1.5752. Min Range: -1.5752

Max Act: 0.9695. Min Act: -0.0000

Data Index: 469029 (The Pile)

Max Activating Token Index: 371

Text #6

Max Range: 1.5752. Min Range: -1.5752

Max Act: 0.9950. Min Act: -0.0000

Data Index: 28237 (The Pile)

Max Activating Token Index: 906

Text #7

Max Range: 1.5752. Min Range: -1.5752

Max Act: 0.9704. Min Act: -0.0000

Data Index: 1646888 (The Pile)

Max Activating Token Index: 571

Text #8

Max Range: 1.5752. Min Range: -1.5752

Max Act: 0.9143. Min Act: -0.0000

Data Index: 1912278 (The Pile)

Max Activating Token Index: 697

Text #9

Max Range: 1.5752. Min Range: -1.5752

Max Act: 0.9712. Min Act: -0.0000

Data Index: 1762979 (The Pile)

Max Activating Token Index: 605

Text #10

Max Range: 1.5752. Min Range: -1.5752

Max Act: 1.0236. Min Act: -0.0000

Data Index: 243818 (The Pile)

Max Activating Token Index: 783

Text #11

Max Range: 1.5752. Min Range: -1.5752

Max Act: 0.9702. Min Act: -0.0000

Data Index: 1725200 (The Pile)

Max Activating Token Index: 210

Text #12

Max Range: 1.5752. Min Range: -1.5752

Max Act: 0.9651. Min Act: -0.0000

Data Index: 1618114 (The Pile)

Max Activating Token Index: 54

Text #13

Max Range: 1.5752. Min Range: -1.5752

Max Act: 0.9953. Min Act: -0.0000

Data Index: 371484 (The Pile)

Max Activating Token Index: 76

Text #14

Max Range: 1.5752. Min Range: -1.5752

Max Act: 0.9795. Min Act: -0.0000

Data Index: 1033048 (The Pile)

Max Activating Token Index: 261

Text #15

Max Range: 1.5752. Min Range: -1.5752

Max Act: 0.9347. Min Act: -0.0000

Data Index: 1914713 (The Pile)

Max Activating Token Index: 632

Text #16

Max Range: 1.5752. Min Range: -1.5752

Max Act: 0.9097. Min Act: -0.0000

Data Index: 1653876 (The Pile)

Max Activating Token Index: 883

Text #17

Max Range: 1.5752. Min Range: -1.5752

Max Act: 0.8840. Min Act: -0.0000

Data Index: 1289650 (The Pile)

Max Activating Token Index: 175

Text #18

Max Range: 1.5752. Min Range: -1.5752

Max Act: 0.8786. Min Act: -0.0000

Data Index: 148943 (The Pile)

Max Activating Token Index: 108

Text #19

Max Range: 1.5752. Min Range: -1.5752

Max Act: 0.8978. Min Act: -0.0000

Data Index: 130347 (The Pile)

Max Activating Token Index: 947