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

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

Neuron 2804 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: 1.0924. Min Range: -1.0924

Max Act: 1.0924. Min Act: -0.0000

Data Index: 198719 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.7417. Min Act: -0.0000

Data Index: 200252 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1153808 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.6780. Min Act: -0.0000

Data Index: 331977 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.6513. Min Act: -0.0000

Data Index: 883752 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.6915. Min Act: -0.0000

Data Index: 288927 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.6482. Min Act: -0.0000

Data Index: 1304710 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.6519. Min Act: -0.0000

Data Index: 63482 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.6189. Min Act: -0.0000

Data Index: 861998 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1073559 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1143507 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.6299. Min Act: -0.0000

Data Index: 183802 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.5806. Min Act: -0.0000

Data Index: 1275450 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.6212. Min Act: -0.0000

Data Index: 497385 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.6140. Min Act: -0.0000

Data Index: 771447 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.5945. Min Act: -0.0000

Data Index: 37004 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.5695. Min Act: -0.0000

Data Index: 481190 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1149367 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.5801. Min Act: -0.0000

Data Index: 734973 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.5616. Min Act: -0.0000

Data Index: 521085 (C4 (Web Text))

Max Activating Token Index: 228