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

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

Neuron 525 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0333. Min Act: -0.0002

Data Index: 1619972 (Python Code)

Max Activating Token Index: 11

Text #1

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0333. Min Act: -0.0002

Data Index: 606074 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1613570 (Python Code)

Max Activating Token Index: 12

Text #3

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0330. Min Act: -0.0002

Data Index: 1376884 (Python Code)

Max Activating Token Index: 16

Text #4

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1611153 (Python Code)

Max Activating Token Index: 36

Text #5

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1631001 (Python Code)

Max Activating Token Index: 101

Text #6

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1404132 (Python Code)

Max Activating Token Index: 18

Text #7

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1627185 (Python Code)

Max Activating Token Index: 10

Text #8

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1464814 (Python Code)

Max Activating Token Index: 10

Text #9

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1386853 (Python Code)

Max Activating Token Index: 33

Text #10

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1437633 (Python Code)

Max Activating Token Index: 21

Text #11

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1365271 (Python Code)

Max Activating Token Index: 6

Text #12

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1443993 (Python Code)

Max Activating Token Index: 8

Text #13

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1373786 (Python Code)

Max Activating Token Index: 23

Text #14

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1590515 (Python Code)

Max Activating Token Index: 11

Text #15

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1483823 (Python Code)

Max Activating Token Index: 26

Text #16

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1381936 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1597803 (Python Code)

Max Activating Token Index: 32

Text #18

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1637728 (Python Code)

Max Activating Token Index: 39

Text #19

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1587335 (Python Code)

Max Activating Token Index: 5