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

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

Neuron 2350 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8218. Min Range: -1.8218

Max Act: 1.8218. Min Act: -0.0000

Data Index: 1209855 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 1.8218. Min Range: -1.8218

Max Act: 1.7250. Min Act: -0.0000

Data Index: 377433 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 1.8218. Min Range: -1.8218

Max Act: 1.6096. Min Act: 0.0000

Data Index: 878486 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 1.8218. Min Range: -1.8218

Max Act: 1.5712. Min Act: -0.0000

Data Index: 1096394 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 1.8218. Min Range: -1.8218

Max Act: 1.5395. Min Act: -0.0000

Data Index: 352253 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 1.8218. Min Range: -1.8218

Max Act: 1.6153. Min Act: -0.0000

Data Index: 762992 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 1.8218. Min Range: -1.8218

Max Act: 1.4915. Min Act: -0.0000

Data Index: 855226 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 1.8218. Min Range: -1.8218

Max Act: 1.5054. Min Act: -0.0000

Data Index: 1053059 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 1.8218. Min Range: -1.8218

Max Act: 1.4741. Min Act: -0.0000

Data Index: 815696 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 1.8218. Min Range: -1.8218

Max Act: 1.4503. Min Act: 0.0000

Data Index: 830094 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 1.8218. Min Range: -1.8218

Max Act: 1.4456. Min Act: 0.0000

Data Index: 1125237 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 1.8218. Min Range: -1.8218

Max Act: 1.3629. Min Act: -0.0000

Data Index: 585353 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 1.8218. Min Range: -1.8218

Max Act: 1.5186. Min Act: -0.0000

Data Index: 384990 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 1.8218. Min Range: -1.8218

Max Act: 1.4239. Min Act: -0.0000

Data Index: 983611 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 1.8218. Min Range: -1.8218

Max Act: 1.4204. Min Act: -0.0000

Data Index: 1031393 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 1.8218. Min Range: -1.8218

Max Act: 1.4649. Min Act: -0.0000

Data Index: 1046813 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 1.8218. Min Range: -1.8218

Max Act: 1.2905. Min Act: 0.0000

Data Index: 688813 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 1.8218. Min Range: -1.8218

Max Act: 1.2874. Min Act: -0.0000

Data Index: 126219 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 1.8218. Min Range: -1.8218

Max Act: 1.4470. Min Act: -0.0000

Data Index: 936064 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 1.8218. Min Range: -1.8218

Max Act: 1.3352. Min Act: -0.0000

Data Index: 931794 (C4 (Web Text))

Max Activating Token Index: 611