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

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

Neuron 220 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.3805. Min Act: -0.0000

Data Index: 1080414 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 2.3805. Min Range: -2.3805

Max Act: 1.6964. Min Act: -0.0000

Data Index: 329015 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 2.3805. Min Range: -2.3805

Max Act: 1.6509. Min Act: -0.0000

Data Index: 1174992 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 2.3805. Min Range: -2.3805

Max Act: 1.5090. Min Act: -0.0000

Data Index: 626558 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 2.3805. Min Range: -2.3805

Max Act: 1.5986. Min Act: -0.0000

Data Index: 1336599 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 2.3805. Min Range: -2.3805

Max Act: 1.5351. Min Act: -0.0000

Data Index: 910602 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 2.3805. Min Range: -2.3805

Max Act: 1.4089. Min Act: -0.0000

Data Index: 6902 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 2.3805. Min Range: -2.3805

Max Act: 1.3989. Min Act: -0.0000

Data Index: 370116 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 2.3805. Min Range: -2.3805

Max Act: 1.4098. Min Act: -0.0000

Data Index: 410176 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 2.3805. Min Range: -2.3805

Max Act: 1.4395. Min Act: -0.0000

Data Index: 480492 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 2.3805. Min Range: -2.3805

Max Act: 1.2736. Min Act: -0.0000

Data Index: 1239650 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 2.3805. Min Range: -2.3805

Max Act: 1.3165. Min Act: -0.0000

Data Index: 929677 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 2.3805. Min Range: -2.3805

Max Act: 1.2894. Min Act: -0.0000

Data Index: 658538 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 2.3805. Min Range: -2.3805

Max Act: 1.3118. Min Act: -0.0000

Data Index: 656188 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 2.3805. Min Range: -2.3805

Max Act: 1.2570. Min Act: -0.0000

Data Index: 1232758 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 2.3805. Min Range: -2.3805

Max Act: 1.3189. Min Act: -0.0000

Data Index: 689120 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 2.3805. Min Range: -2.3805

Max Act: 1.2593. Min Act: -0.0000

Data Index: 907434 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 2.3805. Min Range: -2.3805

Max Act: 1.2162. Min Act: -0.0000

Data Index: 179295 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 2.3805. Min Range: -2.3805

Max Act: 1.2567. Min Act: -0.0000

Data Index: 16494 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 2.3805. Min Range: -2.3805

Max Act: 1.2161. Min Act: -0.0000

Data Index: 429103 (C4 (Web Text))

Max Activating Token Index: 853