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

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

Neuron 3306 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.6250. Min Act: -0.0000

Data Index: 531476 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1087840 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.6023. Min Act: -0.0000

Data Index: 1230064 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.5331. Min Act: -0.0000

Data Index: 759161 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.5971. Min Act: -0.0000

Data Index: 404238 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.5725. Min Act: -0.0000

Data Index: 1216640 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.5705. Min Act: -0.0000

Data Index: 1076739 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.5614. Min Act: -0.0000

Data Index: 270686 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.5412. Min Act: -0.0000

Data Index: 1208921 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.5240. Min Act: -0.0000

Data Index: 589893 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.5548. Min Act: -0.0000

Data Index: 888682 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.5173. Min Act: -0.0000

Data Index: 294677 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.5253. Min Act: -0.0000

Data Index: 1353770 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.5169. Min Act: -0.0000

Data Index: 1006403 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.5594. Min Act: -0.0000

Data Index: 810108 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.4940. Min Act: -0.0000

Data Index: 447247 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.4775. Min Act: -0.0000

Data Index: 344965 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1014180 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.4898. Min Act: -0.0000

Data Index: 893855 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.5027. Min Act: -0.0000

Data Index: 685472 (C4 (Web Text))

Max Activating Token Index: 249