Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3804 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1567052 (Python Code)

Max Activating Token Index: 4

Text #1

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1488200 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1579838 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1391512 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1366137 (Python Code)

Max Activating Token Index: 3

Text #5

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1492657 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1384309 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1427031 (Python Code)

Max Activating Token Index: 3

Text #8

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1638538 (Python Code)

Max Activating Token Index: 3

Text #9

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1632702 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1435791 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1622433 (Python Code)

Max Activating Token Index: 3

Text #12

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1378799 (Python Code)

Max Activating Token Index: 3

Text #13

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1386168 (Python Code)

Max Activating Token Index: 3

Text #14

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1598379 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1593740 (Python Code)

Max Activating Token Index: 3

Text #16

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1501940 (Python Code)

Max Activating Token Index: 4

Text #17

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1402976 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1492453 (Python Code)

Max Activating Token Index: 4

Text #19

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1453878 (Python Code)

Max Activating Token Index: 4