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

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

Neuron 1760 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: 1.1560. Min Range: -1.1560

Max Act: 1.1560. Min Act: -0.0000

Data Index: 770190 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.7602. Min Act: -0.0000

Data Index: 991472 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.7178. Min Act: -0.0000

Data Index: 916714 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.7087. Min Act: -0.0000

Data Index: 700242 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.6969. Min Act: -0.0000

Data Index: 1280251 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.6788. Min Act: -0.0000

Data Index: 1353269 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.6104. Min Act: -0.0000

Data Index: 76470 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.6167. Min Act: -0.0000

Data Index: 845239 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.6135. Min Act: -0.0000

Data Index: 1019371 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.5590. Min Act: -0.0000

Data Index: 286354 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.5610. Min Act: -0.0000

Data Index: 534161 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.5225. Min Act: -0.0000

Data Index: 81003 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.5433. Min Act: -0.0000

Data Index: 1265354 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.5277. Min Act: -0.0000

Data Index: 599893 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.5138. Min Act: -0.0000

Data Index: 391630 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.5609. Min Act: -0.0000

Data Index: 166190 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.5052. Min Act: -0.0000

Data Index: 1292788 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.5532. Min Act: -0.0000

Data Index: 316708 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.5304. Min Act: -0.0000

Data Index: 848889 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.4993. Min Act: -0.0000

Data Index: 956998 (C4 (Web Text))

Max Activating Token Index: 291