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

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

Neuron 5311 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: 1.3098. Min Range: -1.3098

Max Act: 1.2752. Min Act: -0.0000

Data Index: 1320402 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 1.3098. Min Range: -1.3098

Max Act: 1.3098. Min Act: -0.0000

Data Index: 231822 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 1.3098. Min Range: -1.3098

Max Act: 1.1229. Min Act: -0.0000

Data Index: 919975 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 1.3098. Min Range: -1.3098

Max Act: 0.9580. Min Act: -0.0000

Data Index: 459332 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 1.3098. Min Range: -1.3098

Max Act: 0.9063. Min Act: -0.0000

Data Index: 1247957 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 1.3098. Min Range: -1.3098

Max Act: 0.9223. Min Act: -0.0000

Data Index: 697219 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 1.3098. Min Range: -1.3098

Max Act: 0.8428. Min Act: -0.0000

Data Index: 1031609 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 1.3098. Min Range: -1.3098

Max Act: 0.8427. Min Act: -0.0000

Data Index: 573975 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 1.3098. Min Range: -1.3098

Max Act: 0.8857. Min Act: -0.0000

Data Index: 1196817 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 1.3098. Min Range: -1.3098

Max Act: 0.8503. Min Act: -0.0000

Data Index: 785055 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 1.3098. Min Range: -1.3098

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1003271 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 1.3098. Min Range: -1.3098

Max Act: 0.7926. Min Act: -0.0000

Data Index: 1084072 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 1.3098. Min Range: -1.3098

Max Act: 0.7966. Min Act: -0.0000

Data Index: 502510 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 1.3098. Min Range: -1.3098

Max Act: 0.8099. Min Act: -0.0000

Data Index: 1275324 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 1.3098. Min Range: -1.3098

Max Act: 0.7473. Min Act: -0.0000

Data Index: 1367578 (Python Code)

Max Activating Token Index: 809

Text #15

Max Range: 1.3098. Min Range: -1.3098

Max Act: 0.8216. Min Act: -0.0000

Data Index: 50257 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 1.3098. Min Range: -1.3098

Max Act: 0.9093. Min Act: -0.0000

Data Index: 1496868 (Python Code)

Max Activating Token Index: 96

Text #17

Max Range: 1.3098. Min Range: -1.3098

Max Act: 0.7983. Min Act: -0.0000

Data Index: 257716 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 1.3098. Min Range: -1.3098

Max Act: 0.8039. Min Act: -0.0000

Data Index: 1204768 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 1.3098. Min Range: -1.3098

Max Act: 0.8420. Min Act: -0.0000

Data Index: 46536 (C4 (Web Text))

Max Activating Token Index: 211