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

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

Neuron 1806 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3599. Min Range: -7.3599

Max Act: 7.3599. Min Act: -0.0000

Data Index: 840572 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 7.3599. Min Range: -7.3599

Max Act: 6.8870. Min Act: -0.0000

Data Index: 381145 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 7.3599. Min Range: -7.3599

Max Act: 5.6572. Min Act: -0.0000

Data Index: 161093 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 7.3599. Min Range: -7.3599

Max Act: 5.4807. Min Act: -0.0000

Data Index: 1144271 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 7.3599. Min Range: -7.3599

Max Act: 5.5286. Min Act: -0.0000

Data Index: 707422 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 7.3599. Min Range: -7.3599

Max Act: 5.9236. Min Act: -0.0000

Data Index: 88517 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 7.3599. Min Range: -7.3599

Max Act: 5.4324. Min Act: -0.0000

Data Index: 480859 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 7.3599. Min Range: -7.3599

Max Act: 5.4309. Min Act: -0.0000

Data Index: 624228 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 7.3599. Min Range: -7.3599

Max Act: 5.5903. Min Act: -0.0000

Data Index: 1006633 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 7.3599. Min Range: -7.3599

Max Act: 5.0842. Min Act: -0.0000

Data Index: 919861 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 7.3599. Min Range: -7.3599

Max Act: 5.2262. Min Act: -0.0000

Data Index: 970433 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 7.3599. Min Range: -7.3599

Max Act: 4.8516. Min Act: -0.0000

Data Index: 521417 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 7.3599. Min Range: -7.3599

Max Act: 5.3586. Min Act: -0.0000

Data Index: 846456 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 7.3599. Min Range: -7.3599

Max Act: 5.0008. Min Act: -0.0000

Data Index: 11435 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 7.3599. Min Range: -7.3599

Max Act: 4.9746. Min Act: -0.0000

Data Index: 1138898 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 7.3599. Min Range: -7.3599

Max Act: 4.9772. Min Act: -0.0000

Data Index: 1131610 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 7.3599. Min Range: -7.3599

Max Act: 5.0006. Min Act: -0.0000

Data Index: 702679 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 7.3599. Min Range: -7.3599

Max Act: 4.8676. Min Act: -0.0000

Data Index: 1289050 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 7.3599. Min Range: -7.3599

Max Act: 4.9500. Min Act: -0.0000

Data Index: 310026 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 7.3599. Min Range: -7.3599

Max Act: 4.7842. Min Act: -0.0000

Data Index: 1056621 (C4 (Web Text))

Max Activating Token Index: 90