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

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

Neuron 2733 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.2812. Min Act: -0.0000

Data Index: 810888 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.2091. Min Act: -0.0000

Data Index: 548663 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1908. Min Act: -0.0000

Data Index: 740188 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1984. Min Act: -0.0000

Data Index: 1016873 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1992. Min Act: -0.0000

Data Index: 314192 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1915. Min Act: -0.0000

Data Index: 776580 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1885. Min Act: -0.0001

Data Index: 1236573 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1786. Min Act: -0.0001

Data Index: 1301322 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1847. Min Act: -0.0000

Data Index: 122156 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1602. Min Act: -0.0001

Data Index: 1122116 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1559. Min Act: -0.0001

Data Index: 640637 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1642. Min Act: -0.0000

Data Index: 90351 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1537. Min Act: -0.0000

Data Index: 136760 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1484. Min Act: -0.0000

Data Index: 468147 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1648. Min Act: -0.0000

Data Index: 67589 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1631. Min Act: -0.0001

Data Index: 913248 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1510. Min Act: -0.0000

Data Index: 852437 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1387. Min Act: -0.0000

Data Index: 675373 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1385. Min Act: -0.0000

Data Index: 525434 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1423. Min Act: -0.0000

Data Index: 800781 (C4 (Web Text))

Max Activating Token Index: 71