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

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

Neuron 4647 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0916. Min Range: -1.0916

Max Act: 1.0559. Min Act: -0.0001

Data Index: 494357 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 1.0916. Min Range: -1.0916

Max Act: 1.0916. Min Act: -0.0001

Data Index: 911361 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.9960. Min Act: -0.0001

Data Index: 19235 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 1.0916. Min Range: -1.0916

Max Act: 1.0518. Min Act: -0.0001

Data Index: 1012137 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.9806. Min Act: -0.0001

Data Index: 472009 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.9814. Min Act: -0.0001

Data Index: 937427 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.9528. Min Act: -0.0001

Data Index: 124235 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.8931. Min Act: -0.0001

Data Index: 129248 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.9551. Min Act: -0.0001

Data Index: 736811 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.9289. Min Act: -0.0001

Data Index: 18849 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 1.0916. Min Range: -1.0916

Max Act: 1.0238. Min Act: -0.0001

Data Index: 690121 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.7715. Min Act: -0.0001

Data Index: 1291270 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.8546. Min Act: -0.0001

Data Index: 686659 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.8972. Min Act: -0.0001

Data Index: 976941 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.8662. Min Act: -0.0001

Data Index: 881380 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.8457. Min Act: -0.0001

Data Index: 852390 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.8087. Min Act: -0.0001

Data Index: 634071 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.7876. Min Act: -0.0001

Data Index: 940683 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.7453. Min Act: -0.0001

Data Index: 1051708 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.9296. Min Act: -0.0001

Data Index: 900318 (C4 (Web Text))

Max Activating Token Index: 677