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

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

Neuron 4729 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: 0.5403. Min Range: -0.5403

Max Act: 0.5196. Min Act: -0.0001

Data Index: 1005622 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.5323. Min Act: -0.0001

Data Index: 1083338 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.5393. Min Act: -0.0001

Data Index: 285386 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.5306. Min Act: -0.0001

Data Index: 626240 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.5263. Min Act: -0.0001

Data Index: 568817 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.5403. Min Act: -0.0001

Data Index: 477846 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4988. Min Act: -0.0001

Data Index: 692299 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.5101. Min Act: -0.0001

Data Index: 129420 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4917. Min Act: -0.0001

Data Index: 976074 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.5060. Min Act: -0.0001

Data Index: 1506825 (Python Code)

Max Activating Token Index: 760

Text #10

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4800. Min Act: -0.0001

Data Index: 1192736 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.5182. Min Act: -0.0001

Data Index: 1554206 (Python Code)

Max Activating Token Index: 785

Text #12

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4974. Min Act: -0.0001

Data Index: 349057 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4784. Min Act: -0.0001

Data Index: 1115629 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4747. Min Act: -0.0001

Data Index: 1524281 (Python Code)

Max Activating Token Index: 245

Text #15

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4746. Min Act: -0.0001

Data Index: 608297 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4572. Min Act: -0.0001

Data Index: 1050508 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4879. Min Act: -0.0001

Data Index: 1612862 (Python Code)

Max Activating Token Index: 703

Text #18

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4659. Min Act: -0.0001

Data Index: 1336065 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4793. Min Act: -0.0001

Data Index: 1466684 (Python Code)

Max Activating Token Index: 379