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

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

Neuron 4200 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0870. Min Act: -0.0002

Data Index: 5625 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0851. Min Act: -0.0002

Data Index: 157648 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0794. Min Act: -0.0002

Data Index: 954674 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0777. Min Act: -0.0002

Data Index: 554092 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0773. Min Act: -0.0002

Data Index: 980656 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0807. Min Act: -0.0002

Data Index: 1172808 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0773. Min Act: -0.0002

Data Index: 459454 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0767. Min Act: -0.0002

Data Index: 897796 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0764. Min Act: -0.0002

Data Index: 988804 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0782. Min Act: -0.0002

Data Index: 730693 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0719. Min Act: -0.0002

Data Index: 462300 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0747. Min Act: -0.0002

Data Index: 4127 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0744. Min Act: -0.0002

Data Index: 1183995 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0709. Min Act: -0.0002

Data Index: 360316 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0765. Min Act: -0.0002

Data Index: 1009767 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1198912 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0728. Min Act: -0.0002

Data Index: 663461 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0702. Min Act: -0.0002

Data Index: 115075 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0724. Min Act: -0.0002

Data Index: 762181 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0746. Min Act: -0.0002

Data Index: 660631 (C4 (Web Text))

Max Activating Token Index: 222