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

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

Neuron 817 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.6856. Min Range: -8.6856

Max Act: 8.6856. Min Act: -0.0000

Data Index: 1146806 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 8.6856. Min Range: -8.6856

Max Act: 7.3761. Min Act: -0.0001

Data Index: 65415 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 8.6856. Min Range: -8.6856

Max Act: 6.4035. Min Act: -0.0001

Data Index: 713706 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 8.6856. Min Range: -8.6856

Max Act: 6.7687. Min Act: -0.0000

Data Index: 821843 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 8.6856. Min Range: -8.6856

Max Act: 7.0637. Min Act: -0.0000

Data Index: 263313 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 8.6856. Min Range: -8.6856

Max Act: 6.3602. Min Act: -0.0000

Data Index: 804909 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 8.6856. Min Range: -8.6856

Max Act: 6.1542. Min Act: -0.0000

Data Index: 934172 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 8.6856. Min Range: -8.6856

Max Act: 5.7508. Min Act: -0.0001

Data Index: 897133 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 8.6856. Min Range: -8.6856

Max Act: 5.6137. Min Act: -0.0000

Data Index: 998973 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 8.6856. Min Range: -8.6856

Max Act: 6.0871. Min Act: -0.0000

Data Index: 473113 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 8.6856. Min Range: -8.6856

Max Act: 6.1121. Min Act: -0.0001

Data Index: 628758 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 8.6856. Min Range: -8.6856

Max Act: 6.0980. Min Act: -0.0000

Data Index: 498709 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 8.6856. Min Range: -8.6856

Max Act: 6.0496. Min Act: -0.0000

Data Index: 84424 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 8.6856. Min Range: -8.6856

Max Act: 5.0393. Min Act: -0.0000

Data Index: 929292 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 8.6856. Min Range: -8.6856

Max Act: 6.0397. Min Act: -0.0001

Data Index: 401461 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 8.6856. Min Range: -8.6856

Max Act: 6.3709. Min Act: -0.0001

Data Index: 476253 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 8.6856. Min Range: -8.6856

Max Act: 5.2799. Min Act: -0.0000

Data Index: 1125019 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 8.6856. Min Range: -8.6856

Max Act: 6.2346. Min Act: -0.0000

Data Index: 785825 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 8.6856. Min Range: -8.6856

Max Act: 6.0535. Min Act: -0.0000

Data Index: 13563 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 8.6856. Min Range: -8.6856

Max Act: 5.4946. Min Act: -0.0001

Data Index: 760248 (C4 (Web Text))

Max Activating Token Index: 148