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

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

Neuron 3628 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2558. Min Range: -2.2558

Max Act: 2.2179. Min Act: -0.0000

Data Index: 243649 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 2.2558. Min Range: -2.2558

Max Act: 1.9733. Min Act: -0.0000

Data Index: 820217 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 2.2558. Min Range: -2.2558

Max Act: 2.0489. Min Act: -0.0000

Data Index: 262394 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 2.2558. Min Range: -2.2558

Max Act: 2.2558. Min Act: -0.0000

Data Index: 1095495 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 2.2558. Min Range: -2.2558

Max Act: 1.9898. Min Act: -0.0001

Data Index: 1294692 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 2.2558. Min Range: -2.2558

Max Act: 2.0841. Min Act: -0.0000

Data Index: 774776 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 2.2558. Min Range: -2.2558

Max Act: 1.9720. Min Act: -0.0001

Data Index: 1130032 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 2.2558. Min Range: -2.2558

Max Act: 1.9958. Min Act: -0.0001

Data Index: 12472 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 2.2558. Min Range: -2.2558

Max Act: 2.1106. Min Act: -0.0000

Data Index: 911171 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 2.2558. Min Range: -2.2558

Max Act: 1.9813. Min Act: -0.0000

Data Index: 642225 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 2.2558. Min Range: -2.2558

Max Act: 1.7668. Min Act: -0.0001

Data Index: 778686 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 2.2558. Min Range: -2.2558

Max Act: 1.7766. Min Act: -0.0001

Data Index: 441722 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 2.2558. Min Range: -2.2558

Max Act: 1.7675. Min Act: -0.0000

Data Index: 860908 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 2.2558. Min Range: -2.2558

Max Act: 1.8301. Min Act: -0.0001

Data Index: 849586 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 2.2558. Min Range: -2.2558

Max Act: 1.8265. Min Act: -0.0000

Data Index: 718274 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 2.2558. Min Range: -2.2558

Max Act: 1.9199. Min Act: -0.0000

Data Index: 813588 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 2.2558. Min Range: -2.2558

Max Act: 1.7051. Min Act: -0.0000

Data Index: 123057 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 2.2558. Min Range: -2.2558

Max Act: 1.9094. Min Act: -0.0001

Data Index: 121497 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 2.2558. Min Range: -2.2558

Max Act: 1.8197. Min Act: -0.0001

Data Index: 1102212 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 2.2558. Min Range: -2.2558

Max Act: 1.6841. Min Act: -0.0001

Data Index: 827552 (C4 (Web Text))

Max Activating Token Index: 36