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

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

Neuron 3845 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1264192 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6295. Min Act: -0.0000

Data Index: 707591 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6006. Min Act: -0.0000

Data Index: 391929 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6421. Min Act: -0.0000

Data Index: 152241 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6047. Min Act: -0.0000

Data Index: 1026359 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5941. Min Act: -0.0000

Data Index: 96100 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5874. Min Act: -0.0000

Data Index: 246530 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6486. Min Act: -0.0000

Data Index: 299570 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6186. Min Act: -0.0000

Data Index: 538738 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5867. Min Act: -0.0000

Data Index: 1206975 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5574. Min Act: -0.0000

Data Index: 1084073 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5478. Min Act: -0.0000

Data Index: 52551 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5562. Min Act: -0.0000

Data Index: 880667 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5065. Min Act: -0.0000

Data Index: 967276 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5096. Min Act: -0.0000

Data Index: 477945 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5419. Min Act: -0.0000

Data Index: 635975 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5012. Min Act: -0.0000

Data Index: 1314610 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4757. Min Act: -0.0000

Data Index: 1234973 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4806. Min Act: -0.0000

Data Index: 733357 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4252. Min Act: -0.0000

Data Index: 65528 (C4 (Web Text))

Max Activating Token Index: 674