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

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

Neuron 1188 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.7264. Min Act: -0.0000

Data Index: 310708 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.7938. Min Act: -0.0000

Data Index: 108366 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.6716. Min Act: -0.0000

Data Index: 78231 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.4572. Min Act: -0.0000

Data Index: 1162394 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.4384. Min Act: -0.0000

Data Index: 303466 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.2611. Min Act: -0.0000

Data Index: 468495 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.3001. Min Act: -0.0000

Data Index: 918710 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.2824. Min Act: -0.0000

Data Index: 158180 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.2731. Min Act: -0.0000

Data Index: 156606 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.2498. Min Act: -0.0000

Data Index: 878149 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.2258. Min Act: -0.0000

Data Index: 622053 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.2277. Min Act: -0.0000

Data Index: 221965 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.1524. Min Act: -0.0000

Data Index: 77043 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.3098. Min Act: -0.0000

Data Index: 713722 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.0061. Min Act: -0.0000

Data Index: 245930 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.1475. Min Act: -0.0000

Data Index: 129865 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.1357. Min Act: -0.0000

Data Index: 100406 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.2552. Min Act: -0.0000

Data Index: 396147 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.0252. Min Act: -0.0000

Data Index: 1087499 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.0225. Min Act: -0.0000

Data Index: 1327814 (C4 (Web Text))

Max Activating Token Index: 488