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

Dataset: The Pile

Neuron 108 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.7122. Min Act: -0.0000

Data Index: 1438093 (The Pile)

Max Activating Token Index: 629

Text #1

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.6830. Min Act: -0.0000

Data Index: 1163355 (The Pile)

Max Activating Token Index: 155

Text #2

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.6800. Min Act: -0.0000

Data Index: 232929 (The Pile)

Max Activating Token Index: 902

Text #3

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5976. Min Act: -0.0000

Data Index: 1940179 (The Pile)

Max Activating Token Index: 938

Text #4

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.6263. Min Act: -0.0000

Data Index: 1068132 (The Pile)

Max Activating Token Index: 462

Text #5

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.6225. Min Act: -0.0000

Data Index: 1395886 (The Pile)

Max Activating Token Index: 428

Text #6

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1652837 (The Pile)

Max Activating Token Index: 198

Text #7

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.6009. Min Act: -0.0000

Data Index: 221486 (The Pile)

Max Activating Token Index: 109

Text #8

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5746. Min Act: -0.0000

Data Index: 746638 (The Pile)

Max Activating Token Index: 551

Text #9

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1811566 (The Pile)

Max Activating Token Index: 748

Text #10

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.6079. Min Act: -0.0000

Data Index: 208391 (The Pile)

Max Activating Token Index: 812

Text #11

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5683. Min Act: -0.0000

Data Index: 1088480 (The Pile)

Max Activating Token Index: 952

Text #12

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5804. Min Act: -0.0000

Data Index: 1519392 (The Pile)

Max Activating Token Index: 238

Text #13

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1586827 (The Pile)

Max Activating Token Index: 900

Text #14

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5404. Min Act: -0.0000

Data Index: 857319 (The Pile)

Max Activating Token Index: 981

Text #15

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5529. Min Act: -0.0000

Data Index: 511418 (The Pile)

Max Activating Token Index: 757

Text #16

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5532. Min Act: -0.0000

Data Index: 525829 (The Pile)

Max Activating Token Index: 195

Text #17

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1252100 (The Pile)

Max Activating Token Index: 1006

Text #18

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5787. Min Act: -0.0000

Data Index: 1936801 (The Pile)

Max Activating Token Index: 906

Text #19

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1818370 (The Pile)

Max Activating Token Index: 860