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

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

Neuron 2289 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: 0.2912. Min Range: -0.2912

Max Act: 0.2912. Min Act: -0.0000

Data Index: 758490 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2376. Min Act: -0.0000

Data Index: 1279877 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2710. Min Act: -0.0000

Data Index: 257006 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1246463 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2669. Min Act: -0.0000

Data Index: 216924 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2371. Min Act: -0.0000

Data Index: 567449 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2397. Min Act: -0.0000

Data Index: 713697 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.1989. Min Act: -0.0000

Data Index: 1165697 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2380. Min Act: -0.0000

Data Index: 371339 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2496. Min Act: -0.0000

Data Index: 517649 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2248. Min Act: -0.0000

Data Index: 165358 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2055. Min Act: -0.0000

Data Index: 92473 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.1890. Min Act: -0.0000

Data Index: 443829 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2086. Min Act: -0.0000

Data Index: 152901 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2338. Min Act: -0.0000

Data Index: 982149 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2079. Min Act: -0.0000

Data Index: 724781 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2086. Min Act: -0.0000

Data Index: 1060069 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2073. Min Act: -0.0000

Data Index: 584299 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2064. Min Act: -0.0000

Data Index: 1158386 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1140406 (C4 (Web Text))

Max Activating Token Index: 695