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

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

Neuron 4760 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2878. Min Range: -1.2878

Max Act: 1.2878. Min Act: -0.0000

Data Index: 506323 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 1.2878. Min Range: -1.2878

Max Act: 1.0348. Min Act: -0.0000

Data Index: 894029 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.9380. Min Act: -0.0000

Data Index: 374676 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.8959. Min Act: -0.0000

Data Index: 653817 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.8444. Min Act: -0.0000

Data Index: 654408 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.7969. Min Act: -0.0000

Data Index: 1209916 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.8373. Min Act: -0.0001

Data Index: 1058636 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.8042. Min Act: -0.0000

Data Index: 1054425 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.8265. Min Act: -0.0001

Data Index: 750161 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.8248. Min Act: -0.0001

Data Index: 964548 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.7922. Min Act: -0.0000

Data Index: 187332 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.7909. Min Act: -0.0000

Data Index: 1192098 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.7818. Min Act: -0.0000

Data Index: 1057466 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.7731. Min Act: -0.0000

Data Index: 541987 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.7242. Min Act: -0.0000

Data Index: 668890 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.7568. Min Act: -0.0001

Data Index: 385317 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.7373. Min Act: -0.0000

Data Index: 854561 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.7303. Min Act: -0.0000

Data Index: 938021 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.7024. Min Act: -0.0000

Data Index: 143758 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.7861. Min Act: -0.0001

Data Index: 118453 (C4 (Web Text))

Max Activating Token Index: 986