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

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

Neuron 2460 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.4234. Min Act: 0.0001

Data Index: 1520516 (Python Code)

Max Activating Token Index: 14

Text #1

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.3969. Min Act: -0.0000

Data Index: 192247 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.3690. Min Act: -0.0000

Data Index: 508072 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.3692. Min Act: 0.0001

Data Index: 1448854 (Python Code)

Max Activating Token Index: 15

Text #4

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.3799. Min Act: 0.0002

Data Index: 1382703 (Python Code)

Max Activating Token Index: 15

Text #5

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.3462. Min Act: -0.0000

Data Index: 1404284 (Python Code)

Max Activating Token Index: 895

Text #6

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.3666. Min Act: -0.0000

Data Index: 1596959 (Python Code)

Max Activating Token Index: 14

Text #7

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.3577. Min Act: -0.0000

Data Index: 1520495 (Python Code)

Max Activating Token Index: 21

Text #8

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.3690. Min Act: -0.0000

Data Index: 1027473 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1393551 (Python Code)

Max Activating Token Index: 11

Text #10

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.3505. Min Act: -0.0000

Data Index: 347124 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.3293. Min Act: 0.0000

Data Index: 1535310 (Python Code)

Max Activating Token Index: 23

Text #12

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.3280. Min Act: 0.0002

Data Index: 1380770 (Python Code)

Max Activating Token Index: 22

Text #13

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.3238. Min Act: 0.0001

Data Index: 1541660 (Python Code)

Max Activating Token Index: 13

Text #14

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.3221. Min Act: -0.0000

Data Index: 1181957 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.3218. Min Act: 0.0001

Data Index: 1495855 (Python Code)

Max Activating Token Index: 21

Text #16

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.3296. Min Act: 0.0001

Data Index: 1437868 (Python Code)

Max Activating Token Index: 23

Text #17

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.3011. Min Act: -0.0000

Data Index: 797958 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.3136. Min Act: -0.0000

Data Index: 1452717 (Python Code)

Max Activating Token Index: 22

Text #19

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.2938. Min Act: -0.0000

Data Index: 688738 (C4 (Web Text))

Max Activating Token Index: 290