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

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

Neuron 2818 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.2922. Min Act: -0.0000

Data Index: 432533 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.2830. Min Act: -0.0000

Data Index: 636638 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.1938. Min Act: -0.0000

Data Index: 876305 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.1727. Min Act: -0.0000

Data Index: 905632 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.1862. Min Act: -0.0000

Data Index: 1298837 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.0244. Min Act: -0.0000

Data Index: 158753 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.0316. Min Act: -0.0000

Data Index: 142758 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.0272. Min Act: -0.0000

Data Index: 418140 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.1075. Min Act: -0.0000

Data Index: 27389 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9669. Min Act: -0.0000

Data Index: 936339 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.0661. Min Act: -0.0000

Data Index: 439460 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9666. Min Act: -0.0000

Data Index: 1306385 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.0342. Min Act: -0.0000

Data Index: 588866 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9715. Min Act: -0.0000

Data Index: 860838 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9186. Min Act: -0.0000

Data Index: 422779 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.0051. Min Act: -0.0000

Data Index: 83877 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.0024. Min Act: -0.0000

Data Index: 654109 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9724. Min Act: -0.0000

Data Index: 673396 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9583. Min Act: -0.0000

Data Index: 961040 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9541. Min Act: -0.0000

Data Index: 1092383 (C4 (Web Text))

Max Activating Token Index: 797