Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 546 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.6868. Min Act: -0.0004

Data Index: 882203 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.6349. Min Act: -0.0004

Data Index: 927420 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.6431. Min Act: -0.0004

Data Index: 1329333 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.5591. Min Act: -0.0004

Data Index: 790687 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.6548. Min Act: -0.0004

Data Index: 1091088 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.6183. Min Act: -0.0004

Data Index: 265596 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.5960. Min Act: -0.0004

Data Index: 97906 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.6379. Min Act: -0.0004

Data Index: 887126 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.5788. Min Act: -0.0004

Data Index: 302585 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.5536. Min Act: -0.0004

Data Index: 1265743 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.5512. Min Act: -0.0004

Data Index: 561425 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.5685. Min Act: -0.0004

Data Index: 964517 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.5477. Min Act: -0.0004

Data Index: 588271 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.5831. Min Act: -0.0004

Data Index: 853454 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.5995. Min Act: -0.0004

Data Index: 1036748 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.5613. Min Act: -0.0004

Data Index: 1111074 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.5419. Min Act: -0.0004

Data Index: 750154 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.5378. Min Act: -0.0004

Data Index: 343957 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.5395. Min Act: -0.0004

Data Index: 292495 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.5735. Min Act: -0.0004

Data Index: 898487 (C4 (Web Text))

Max Activating Token Index: 261