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

Dataset: The Pile

Neuron 1584 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.7172. Min Act: -0.0000

Data Index: 937801 (The Pile)

Max Activating Token Index: 353

Text #1

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6754. Min Act: -0.0000

Data Index: 1180718 (The Pile)

Max Activating Token Index: 956

Text #2

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6026. Min Act: -0.0000

Data Index: 966345 (The Pile)

Max Activating Token Index: 853

Text #3

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6672. Min Act: -0.0000

Data Index: 1093007 (The Pile)

Max Activating Token Index: 524

Text #4

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5741. Min Act: -0.0000

Data Index: 1776801 (The Pile)

Max Activating Token Index: 571

Text #5

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6654. Min Act: -0.0000

Data Index: 49977 (The Pile)

Max Activating Token Index: 129

Text #6

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6143. Min Act: -0.0000

Data Index: 568479 (The Pile)

Max Activating Token Index: 138

Text #7

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5423. Min Act: -0.0000

Data Index: 1595865 (The Pile)

Max Activating Token Index: 953

Text #8

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5656. Min Act: -0.0000

Data Index: 1653347 (The Pile)

Max Activating Token Index: 45

Text #9

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6122. Min Act: -0.0000

Data Index: 177612 (The Pile)

Max Activating Token Index: 306

Text #10

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5928. Min Act: -0.0000

Data Index: 148272 (The Pile)

Max Activating Token Index: 226

Text #11

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5537. Min Act: -0.0000

Data Index: 590338 (The Pile)

Max Activating Token Index: 960

Text #12

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5585. Min Act: -0.0000

Data Index: 1783091 (The Pile)

Max Activating Token Index: 164

Text #13

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6044. Min Act: -0.0000

Data Index: 994965 (The Pile)

Max Activating Token Index: 940

Text #14

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5946. Min Act: -0.0000

Data Index: 1642016 (The Pile)

Max Activating Token Index: 578

Text #15

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1198152 (The Pile)

Max Activating Token Index: 752

Text #16

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5947. Min Act: -0.0000

Data Index: 174652 (The Pile)

Max Activating Token Index: 541

Text #17

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1043397 (The Pile)

Max Activating Token Index: 182

Text #18

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1761997 (The Pile)

Max Activating Token Index: 106

Text #19

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5657. Min Act: -0.0000

Data Index: 1037035 (The Pile)

Max Activating Token Index: 162