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

Dataset: The Pile

Neuron 2010 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: 1.0514. Min Range: -1.0514

Max Act: 1.0514. Min Act: -0.0000

Data Index: 840226 (The Pile)

Max Activating Token Index: 178

Text #1

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.9949. Min Act: -0.0000

Data Index: 1419975 (The Pile)

Max Activating Token Index: 684

Text #2

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.8670. Min Act: -0.0000

Data Index: 1409417 (The Pile)

Max Activating Token Index: 157

Text #3

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.8639. Min Act: 0.0000

Data Index: 912537 (The Pile)

Max Activating Token Index: 569

Text #4

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.9006. Min Act: -0.0000

Data Index: 260697 (The Pile)

Max Activating Token Index: 660

Text #5

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.8811. Min Act: -0.0000

Data Index: 320979 (The Pile)

Max Activating Token Index: 40

Text #6

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7910. Min Act: -0.0000

Data Index: 1663226 (The Pile)

Max Activating Token Index: 120

Text #7

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7809. Min Act: -0.0000

Data Index: 341984 (The Pile)

Max Activating Token Index: 632

Text #8

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.8272. Min Act: -0.0000

Data Index: 102591 (The Pile)

Max Activating Token Index: 958

Text #9

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7964. Min Act: 0.0000

Data Index: 1861585 (The Pile)

Max Activating Token Index: 738

Text #10

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7825. Min Act: -0.0000

Data Index: 767908 (The Pile)

Max Activating Token Index: 93

Text #11

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7846. Min Act: -0.0000

Data Index: 891635 (The Pile)

Max Activating Token Index: 798

Text #12

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7631. Min Act: 0.0000

Data Index: 1751846 (The Pile)

Max Activating Token Index: 228

Text #13

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.8393. Min Act: -0.0000

Data Index: 1646249 (The Pile)

Max Activating Token Index: 108

Text #14

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7695. Min Act: -0.0000

Data Index: 1931428 (The Pile)

Max Activating Token Index: 402

Text #15

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7525. Min Act: 0.0000

Data Index: 1725911 (The Pile)

Max Activating Token Index: 746

Text #16

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.8391. Min Act: -0.0000

Data Index: 1620670 (The Pile)

Max Activating Token Index: 960

Text #17

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7515. Min Act: -0.0000

Data Index: 178367 (The Pile)

Max Activating Token Index: 467

Text #18

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7008. Min Act: -0.0000

Data Index: 216564 (The Pile)

Max Activating Token Index: 482

Text #19

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1184116 (The Pile)

Max Activating Token Index: 21