Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2408 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.4763. Min Act: -0.0001

Data Index: 502554 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.2513. Min Act: -0.0000

Data Index: 1325798 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.2811. Min Act: -0.0001

Data Index: 1348378 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.2441. Min Act: -0.0000

Data Index: 1023139 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.1577. Min Act: -0.0001

Data Index: 1024551 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.2289. Min Act: -0.0001

Data Index: 1004438 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.0934. Min Act: -0.0000

Data Index: 941349 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.0799. Min Act: -0.0000

Data Index: 1240246 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.0814. Min Act: -0.0001

Data Index: 824979 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.0455. Min Act: -0.0001

Data Index: 1352890 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.0351. Min Act: -0.0001

Data Index: 847946 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.1240. Min Act: -0.0000

Data Index: 1156909 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.1032. Min Act: -0.0000

Data Index: 1052491 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.0426. Min Act: -0.0001

Data Index: 522483 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 1.4763. Min Range: -1.4763

Max Act: 0.9960. Min Act: -0.0001

Data Index: 1060245 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.0572. Min Act: -0.0001

Data Index: 825338 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.0462. Min Act: -0.0000

Data Index: 1284170 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.0018. Min Act: -0.0000

Data Index: 1250565 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 1.4763. Min Range: -1.4763

Max Act: 0.9605. Min Act: -0.0001

Data Index: 775697 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 1.4763. Min Range: -1.4763

Max Act: 0.9601. Min Act: -0.0001

Data Index: 1056529 (C4 (Web Text))

Max Activating Token Index: 977