Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4567 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7746. Min Range: -2.7746

Max Act: 2.7440. Min Act: -0.0000

Data Index: 603390 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 2.7746. Min Range: -2.7746

Max Act: 2.7746. Min Act: -0.0000

Data Index: 312831 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 2.7746. Min Range: -2.7746

Max Act: 2.7318. Min Act: -0.0000

Data Index: 721563 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 2.7746. Min Range: -2.7746

Max Act: 2.5956. Min Act: -0.0000

Data Index: 442791 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 2.7746. Min Range: -2.7746

Max Act: 2.4447. Min Act: -0.0000

Data Index: 69924 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 2.7746. Min Range: -2.7746

Max Act: 2.3998. Min Act: -0.0000

Data Index: 1068477 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 2.7746. Min Range: -2.7746

Max Act: 2.2458. Min Act: -0.0000

Data Index: 921192 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 2.7746. Min Range: -2.7746

Max Act: 2.0492. Min Act: -0.0000

Data Index: 1211447 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 2.7746. Min Range: -2.7746

Max Act: 2.0254. Min Act: -0.0000

Data Index: 568696 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 2.7746. Min Range: -2.7746

Max Act: 1.9806. Min Act: -0.0000

Data Index: 1249169 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 2.7746. Min Range: -2.7746

Max Act: 1.8274. Min Act: -0.0000

Data Index: 1150806 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 2.7746. Min Range: -2.7746

Max Act: 1.9232. Min Act: -0.0000

Data Index: 340788 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 2.7746. Min Range: -2.7746

Max Act: 1.7842. Min Act: -0.0000

Data Index: 1105106 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 2.7746. Min Range: -2.7746

Max Act: 1.7675. Min Act: -0.0000

Data Index: 874226 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 2.7746. Min Range: -2.7746

Max Act: 1.9829. Min Act: -0.0000

Data Index: 324808 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 2.7746. Min Range: -2.7746

Max Act: 1.9755. Min Act: -0.0000

Data Index: 133441 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 2.7746. Min Range: -2.7746

Max Act: 1.8063. Min Act: -0.0000

Data Index: 443572 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 2.7746. Min Range: -2.7746

Max Act: 1.6999. Min Act: -0.0000

Data Index: 1005609 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 2.7746. Min Range: -2.7746

Max Act: 1.7737. Min Act: -0.0000

Data Index: 751355 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 2.7746. Min Range: -2.7746

Max Act: 1.7924. Min Act: -0.0000

Data Index: 94377 (C4 (Web Text))

Max Activating Token Index: 68