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

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

Neuron 1965 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.8747. Min Act: -0.0000

Data Index: 761906 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7254. Min Act: -0.0000

Data Index: 707100 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.6560. Min Act: -0.0000

Data Index: 120987 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1179853 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.6669. Min Act: -0.0000

Data Index: 193742 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.6639. Min Act: -0.0000

Data Index: 159342 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.6717. Min Act: -0.0000

Data Index: 36121 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.6454. Min Act: -0.0000

Data Index: 965602 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.6253. Min Act: -0.0000

Data Index: 464397 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.6142. Min Act: -0.0000

Data Index: 11443 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.6126. Min Act: -0.0000

Data Index: 965077 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.6280. Min Act: -0.0000

Data Index: 995361 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.6239. Min Act: -0.0000

Data Index: 762401 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.6242. Min Act: -0.0000

Data Index: 724330 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.6386. Min Act: -0.0000

Data Index: 896384 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1053997 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.6035. Min Act: -0.0000

Data Index: 101509 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.6000. Min Act: -0.0000

Data Index: 891445 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.5941. Min Act: -0.0000

Data Index: 829348 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.6061. Min Act: -0.0000

Data Index: 943874 (C4 (Web Text))

Max Activating Token Index: 315