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

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

Neuron 741 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2767. Min Act: -0.0000

Data Index: 1059716 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2485. Min Act: -0.0000

Data Index: 228491 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2488. Min Act: -0.0000

Data Index: 288102 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2364. Min Act: 0.0000

Data Index: 363712 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2417. Min Act: -0.0000

Data Index: 651288 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2404. Min Act: -0.0000

Data Index: 826452 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2393. Min Act: -0.0000

Data Index: 958608 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2169. Min Act: -0.0000

Data Index: 299896 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2058. Min Act: -0.0000

Data Index: 477369 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2125. Min Act: -0.0000

Data Index: 418927 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1976. Min Act: -0.0000

Data Index: 629033 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1977. Min Act: -0.0000

Data Index: 442090 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1932. Min Act: -0.0000

Data Index: 161716 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1919. Min Act: -0.0000

Data Index: 166552 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1865. Min Act: -0.0000

Data Index: 641696 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1917. Min Act: -0.0000

Data Index: 478281 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1870. Min Act: -0.0000

Data Index: 414201 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1841. Min Act: -0.0000

Data Index: 541364 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1723. Min Act: -0.0000

Data Index: 946273 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1833. Min Act: -0.0000

Data Index: 599917 (C4 (Web Text))

Max Activating Token Index: 66