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

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

Neuron 2680 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.5092. Min Act: -0.0000

Data Index: 572762 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.5072. Min Act: -0.0000

Data Index: 90869 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4515. Min Act: -0.0000

Data Index: 609392 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4839. Min Act: -0.0000

Data Index: 628645 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4249. Min Act: -0.0000

Data Index: 913125 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4460. Min Act: -0.0000

Data Index: 570931 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1320803 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4791. Min Act: -0.0000

Data Index: 1335582 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4352. Min Act: -0.0000

Data Index: 1423234 (Python Code)

Max Activating Token Index: 811

Text #9

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4433. Min Act: -0.0000

Data Index: 1282009 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.3902. Min Act: -0.0000

Data Index: 1582277 (Python Code)

Max Activating Token Index: 247

Text #11

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4322. Min Act: -0.0000

Data Index: 860872 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4392. Min Act: -0.0000

Data Index: 1164137 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1406091 (Python Code)

Max Activating Token Index: 805

Text #14

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4236. Min Act: -0.0000

Data Index: 1600577 (Python Code)

Max Activating Token Index: 347

Text #15

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4121. Min Act: -0.0000

Data Index: 1458600 (Python Code)

Max Activating Token Index: 29

Text #16

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4318. Min Act: -0.0000

Data Index: 1384014 (Python Code)

Max Activating Token Index: 698

Text #17

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4109. Min Act: -0.0000

Data Index: 1500079 (Python Code)

Max Activating Token Index: 64

Text #18

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4007. Min Act: -0.0000

Data Index: 1328893 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4205. Min Act: -0.0000

Data Index: 1527680 (Python Code)

Max Activating Token Index: 327