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

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

Neuron 3831 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: 0.5120. Min Range: -0.5120

Max Act: 0.5118. Min Act: -0.0000

Data Index: 1552525 (Python Code)

Max Activating Token Index: 215

Text #1

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.5120. Min Act: -0.0000

Data Index: 1356118 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4984. Min Act: -0.0000

Data Index: 1612740 (Python Code)

Max Activating Token Index: 196

Text #3

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4340. Min Act: 0.0002

Data Index: 532248 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4257. Min Act: -0.0000

Data Index: 743464 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4271. Min Act: -0.0000

Data Index: 1514634 (Python Code)

Max Activating Token Index: 296

Text #6

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3948. Min Act: 0.0000

Data Index: 519630 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4179. Min Act: -0.0000

Data Index: 1613544 (Python Code)

Max Activating Token Index: 258

Text #8

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3876. Min Act: -0.0000

Data Index: 1363491 (Python Code)

Max Activating Token Index: 132

Text #9

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3963. Min Act: -0.0000

Data Index: 892500 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3866. Min Act: -0.0000

Data Index: 1529260 (Python Code)

Max Activating Token Index: 300

Text #11

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3753. Min Act: -0.0000

Data Index: 1437741 (Python Code)

Max Activating Token Index: 709

Text #12

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3888. Min Act: -0.0000

Data Index: 1376595 (Python Code)

Max Activating Token Index: 285

Text #13

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3598. Min Act: 0.0000

Data Index: 1580415 (Python Code)

Max Activating Token Index: 494

Text #14

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3738. Min Act: -0.0000

Data Index: 1595781 (Python Code)

Max Activating Token Index: 391

Text #15

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3717. Min Act: -0.0000

Data Index: 1027047 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3679. Min Act: 0.0000

Data Index: 1554087 (Python Code)

Max Activating Token Index: 497

Text #17

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3569. Min Act: -0.0000

Data Index: 113627 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3630. Min Act: -0.0000

Data Index: 353568 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3620. Min Act: 0.0001

Data Index: 1627640 (Python Code)

Max Activating Token Index: 775