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

Dataset: The Pile

Neuron 2773 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.4446. Min Act: -0.0000

Data Index: 94649 (The Pile)

Max Activating Token Index: 495

Text #1

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.4446. Min Act: -0.0000

Data Index: 1519937 (The Pile)

Max Activating Token Index: 878

Text #2

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.5008. Min Act: -0.0000

Data Index: 658853 (The Pile)

Max Activating Token Index: 570

Text #3

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.5022. Min Act: -0.0000

Data Index: 1545422 (The Pile)

Max Activating Token Index: 424

Text #4

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.5683. Min Act: -0.0000

Data Index: 1810604 (The Pile)

Max Activating Token Index: 952

Text #5

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.3783. Min Act: -0.0000

Data Index: 1141616 (The Pile)

Max Activating Token Index: 337

Text #6

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.4354. Min Act: -0.0000

Data Index: 147578 (The Pile)

Max Activating Token Index: 753

Text #7

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.4099. Min Act: -0.0000

Data Index: 1498536 (The Pile)

Max Activating Token Index: 175

Text #8

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.3164. Min Act: -0.0000

Data Index: 1350976 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.2829. Min Act: -0.0000

Data Index: 1776200 (The Pile)

Max Activating Token Index: 868

Text #10

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.2353. Min Act: -0.0000

Data Index: 216579 (The Pile)

Max Activating Token Index: 503

Text #11

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.1535. Min Act: -0.0000

Data Index: 1723873 (The Pile)

Max Activating Token Index: 691

Text #12

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.2004. Min Act: -0.0000

Data Index: 146397 (The Pile)

Max Activating Token Index: 985

Text #13

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.2969. Min Act: -0.0000

Data Index: 978205 (The Pile)

Max Activating Token Index: 320

Text #14

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.2842. Min Act: -0.0000

Data Index: 772892 (The Pile)

Max Activating Token Index: 804

Text #15

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.2354. Min Act: -0.0000

Data Index: 1150236 (The Pile)

Max Activating Token Index: 866

Text #16

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.2410. Min Act: -0.0000

Data Index: 365274 (The Pile)

Max Activating Token Index: 662

Text #17

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.2307. Min Act: -0.0000

Data Index: 1576794 (The Pile)

Max Activating Token Index: 389

Text #18

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.2190. Min Act: -0.0000

Data Index: 1914385 (The Pile)

Max Activating Token Index: 908

Text #19

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.2295. Min Act: -0.0000

Data Index: 1171624 (The Pile)

Max Activating Token Index: 178