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

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

Neuron 1644 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1183. Min Act: -0.0001

Data Index: 392607 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0943. Min Act: -0.0001

Data Index: 1068262 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0889. Min Act: -0.0001

Data Index: 597146 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0817. Min Act: -0.0001

Data Index: 490887 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0865. Min Act: -0.0001

Data Index: 430430 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0807. Min Act: -0.0001

Data Index: 1231738 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0794. Min Act: -0.0001

Data Index: 1091496 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0803. Min Act: -0.0001

Data Index: 1148610 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0789. Min Act: -0.0001

Data Index: 1205855 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0731. Min Act: -0.0001

Data Index: 724355 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0760. Min Act: -0.0001

Data Index: 579506 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0781. Min Act: -0.0001

Data Index: 619541 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0796. Min Act: -0.0001

Data Index: 150511 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0692. Min Act: -0.0001

Data Index: 705979 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0736. Min Act: -0.0001

Data Index: 548433 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0708. Min Act: -0.0001

Data Index: 552110 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0732. Min Act: -0.0001

Data Index: 69689 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0756. Min Act: -0.0001

Data Index: 620914 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0730. Min Act: -0.0001

Data Index: 144100 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0723. Min Act: -0.0001

Data Index: 530409 (C4 (Web Text))

Max Activating Token Index: 239