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

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

Neuron 3010 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: 0.9985. Min Range: -0.9985

Max Act: 0.9985. Min Act: -0.0000

Data Index: 526890 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.9294. Min Act: -0.0000

Data Index: 1223423 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.9037. Min Act: -0.0000

Data Index: 1193262 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.9311. Min Act: -0.0000

Data Index: 1354718 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1033108 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.8438. Min Act: -0.0000

Data Index: 699980 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.8421. Min Act: -0.0000

Data Index: 369958 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.7888. Min Act: -0.0000

Data Index: 1013931 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.8038. Min Act: -0.0000

Data Index: 932482 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.7753. Min Act: -0.0000

Data Index: 248590 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.7917. Min Act: -0.0000

Data Index: 53834 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.7931. Min Act: -0.0000

Data Index: 727007 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.7901. Min Act: -0.0000

Data Index: 1194777 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.7627. Min Act: -0.0000

Data Index: 31399 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.7886. Min Act: -0.0000

Data Index: 355620 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.7896. Min Act: -0.0000

Data Index: 508496 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.8135. Min Act: -0.0000

Data Index: 604452 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.7828. Min Act: -0.0000

Data Index: 122858 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.7570. Min Act: -0.0000

Data Index: 459481 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.7777. Min Act: -0.0000

Data Index: 199588 (C4 (Web Text))

Max Activating Token Index: 643