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

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

Neuron 5830 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1992. Min Range: -5.1992

Max Act: 5.1992. Min Act: -0.0000

Data Index: 219608 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 5.1992. Min Range: -5.1992

Max Act: 3.7968. Min Act: -0.0000

Data Index: 191756 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 5.1992. Min Range: -5.1992

Max Act: 3.6740. Min Act: -0.0000

Data Index: 644595 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 5.1992. Min Range: -5.1992

Max Act: 3.5105. Min Act: -0.0000

Data Index: 1020495 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 5.1992. Min Range: -5.1992

Max Act: 3.4572. Min Act: -0.0000

Data Index: 653859 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 5.1992. Min Range: -5.1992

Max Act: 3.4408. Min Act: -0.0000

Data Index: 1100002 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 5.1992. Min Range: -5.1992

Max Act: 3.3796. Min Act: -0.0000

Data Index: 741093 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 5.1992. Min Range: -5.1992

Max Act: 3.5887. Min Act: -0.0000

Data Index: 982919 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 5.1992. Min Range: -5.1992

Max Act: 3.0874. Min Act: -0.0000

Data Index: 391049 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 5.1992. Min Range: -5.1992

Max Act: 3.2039. Min Act: -0.0000

Data Index: 868308 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 5.1992. Min Range: -5.1992

Max Act: 3.3277. Min Act: -0.0000

Data Index: 921183 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 5.1992. Min Range: -5.1992

Max Act: 3.3159. Min Act: -0.0000

Data Index: 1016185 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 5.1992. Min Range: -5.1992

Max Act: 3.1306. Min Act: -0.0000

Data Index: 63966 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 5.1992. Min Range: -5.1992

Max Act: 3.2203. Min Act: -0.0000

Data Index: 1358675 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 5.1992. Min Range: -5.1992

Max Act: 3.0481. Min Act: -0.0000

Data Index: 672742 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 5.1992. Min Range: -5.1992

Max Act: 2.9074. Min Act: -0.0000

Data Index: 827789 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 5.1992. Min Range: -5.1992

Max Act: 3.0527. Min Act: -0.0000

Data Index: 1110810 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 5.1992. Min Range: -5.1992

Max Act: 3.0477. Min Act: -0.0000

Data Index: 197651 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 5.1992. Min Range: -5.1992

Max Act: 3.1349. Min Act: -0.0000

Data Index: 757024 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 5.1992. Min Range: -5.1992

Max Act: 2.9909. Min Act: -0.0000

Data Index: 462424 (C4 (Web Text))

Max Activating Token Index: 830