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

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

Neuron 2848 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: 1.1042. Min Range: -1.1042

Max Act: 1.1042. Min Act: -0.0000

Data Index: 208177 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.9606. Min Act: -0.0000

Data Index: 379460 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.8907. Min Act: -0.0000

Data Index: 448345 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 1.1042. Min Range: -1.1042

Max Act: 1.0051. Min Act: -0.0000

Data Index: 1013412 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.8336. Min Act: -0.0000

Data Index: 950336 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.8961. Min Act: -0.0000

Data Index: 515317 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.9092. Min Act: -0.0000

Data Index: 101819 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.8674. Min Act: -0.0000

Data Index: 823968 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.8232. Min Act: -0.0000

Data Index: 608908 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.9055. Min Act: -0.0000

Data Index: 1332098 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.8513. Min Act: -0.0000

Data Index: 733392 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.8148. Min Act: -0.0000

Data Index: 778455 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.8527. Min Act: -0.0001

Data Index: 179897 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.8299. Min Act: -0.0000

Data Index: 137643 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.8231. Min Act: -0.0000

Data Index: 1027720 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1090817 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.7890. Min Act: -0.0000

Data Index: 406675 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.7884. Min Act: -0.0000

Data Index: 548540 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.7962. Min Act: -0.0000

Data Index: 1137015 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.7657. Min Act: -0.0000

Data Index: 837604 (C4 (Web Text))

Max Activating Token Index: 277