Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1453 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.3774. Min Act: -0.0000

Data Index: 733913 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.3475. Min Act: -0.0000

Data Index: 1023822 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.3667. Min Act: -0.0000

Data Index: 290851 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.3423. Min Act: -0.0000

Data Index: 18085 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.3405. Min Act: -0.0000

Data Index: 36283 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.3148. Min Act: -0.0000

Data Index: 725893 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.3118. Min Act: -0.0000

Data Index: 778174 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.3139. Min Act: -0.0000

Data Index: 979475 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.3034. Min Act: -0.0000

Data Index: 295893 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2887. Min Act: -0.0000

Data Index: 994835 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2943. Min Act: -0.0000

Data Index: 1177692 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2891. Min Act: -0.0000

Data Index: 198383 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2876. Min Act: -0.0000

Data Index: 565855 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.3048. Min Act: -0.0000

Data Index: 32885 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.3039. Min Act: -0.0000

Data Index: 781732 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2842. Min Act: -0.0000

Data Index: 171146 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2927. Min Act: -0.0000

Data Index: 595487 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.3035. Min Act: -0.0000

Data Index: 915393 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2825. Min Act: -0.0000

Data Index: 881520 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.3008. Min Act: -0.0000

Data Index: 11686 (C4 (Web Text))

Max Activating Token Index: 616