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

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

Neuron 3075 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.9916. Min Act: -0.0000

Data Index: 131275 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.9281. Min Act: -0.0000

Data Index: 390432 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7839. Min Act: -0.0000

Data Index: 643641 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.8232. Min Act: -0.0000

Data Index: 1331723 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7793. Min Act: -0.0000

Data Index: 1141915 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7252. Min Act: -0.0000

Data Index: 678639 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7792. Min Act: -0.0000

Data Index: 163255 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7486. Min Act: -0.0000

Data Index: 609223 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7373. Min Act: -0.0000

Data Index: 571614 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7035. Min Act: -0.0000

Data Index: 70806 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7119. Min Act: -0.0000

Data Index: 115356 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1491798 (Python Code)

Max Activating Token Index: 134

Text #12

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1068868 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.6769. Min Act: -0.0000

Data Index: 971190 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.6592. Min Act: -0.0000

Data Index: 1460272 (Python Code)

Max Activating Token Index: 840

Text #15

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.6539. Min Act: -0.0000

Data Index: 278364 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.6330. Min Act: -0.0000

Data Index: 1048031 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.6228. Min Act: -0.0000

Data Index: 752903 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.5935. Min Act: -0.0000

Data Index: 1604167 (Python Code)

Max Activating Token Index: 221

Text #19

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.6271. Min Act: -0.0000

Data Index: 144215 (C4 (Web Text))

Max Activating Token Index: 574