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

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

Neuron 5367 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1437. Min Act: -0.0000

Data Index: 81630 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1450. Min Act: -0.0000

Data Index: 817430 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1125. Min Act: -0.0000

Data Index: 296137 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1015. Min Act: -0.0000

Data Index: 779415 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.0960. Min Act: -0.0000

Data Index: 858727 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1025. Min Act: -0.0000

Data Index: 641986 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.0935. Min Act: -0.0000

Data Index: 1198534 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.0940. Min Act: -0.0000

Data Index: 1088761 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.0928. Min Act: -0.0000

Data Index: 214861 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.0941. Min Act: -0.0000

Data Index: 209435 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.0867. Min Act: -0.0000

Data Index: 1023037 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1310078 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.0877. Min Act: -0.0000

Data Index: 584107 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.0979. Min Act: -0.0000

Data Index: 206333 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.0921. Min Act: -0.0000

Data Index: 475181 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.0824. Min Act: -0.0000

Data Index: 639326 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.0883. Min Act: -0.0000

Data Index: 556193 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.0853. Min Act: -0.0000

Data Index: 363523 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.0806. Min Act: -0.0000

Data Index: 20323 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.0880. Min Act: -0.0001

Data Index: 989424 (C4 (Web Text))

Max Activating Token Index: 337