Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 492 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6077. Min Range: -1.6077

Max Act: 1.6077. Min Act: -0.0000

Data Index: 1024255 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 1.6077. Min Range: -1.6077

Max Act: 1.4084. Min Act: 0.0000

Data Index: 820599 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 1.6077. Min Range: -1.6077

Max Act: 1.0995. Min Act: -0.0000

Data Index: 739057 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 1.6077. Min Range: -1.6077

Max Act: 1.1468. Min Act: -0.0000

Data Index: 1086112 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 1.6077. Min Range: -1.6077

Max Act: 1.0480. Min Act: -0.0000

Data Index: 459345 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 1.6077. Min Range: -1.6077

Max Act: 0.9219. Min Act: -0.0000

Data Index: 93584 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 1.6077. Min Range: -1.6077

Max Act: 0.9479. Min Act: -0.0000

Data Index: 322891 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 1.6077. Min Range: -1.6077

Max Act: 0.9280. Min Act: -0.0000

Data Index: 1012268 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 1.6077. Min Range: -1.6077

Max Act: 0.8984. Min Act: -0.0000

Data Index: 199913 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 1.6077. Min Range: -1.6077

Max Act: 0.8999. Min Act: -0.0000

Data Index: 1102291 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 1.6077. Min Range: -1.6077

Max Act: 0.8869. Min Act: -0.0000

Data Index: 144886 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 1.6077. Min Range: -1.6077

Max Act: 0.9818. Min Act: -0.0000

Data Index: 1181519 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 1.6077. Min Range: -1.6077

Max Act: 0.8592. Min Act: -0.0000

Data Index: 426859 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 1.6077. Min Range: -1.6077

Max Act: 0.8253. Min Act: -0.0000

Data Index: 1167691 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 1.6077. Min Range: -1.6077

Max Act: 0.9793. Min Act: -0.0000

Data Index: 975104 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 1.6077. Min Range: -1.6077

Max Act: 0.8363. Min Act: -0.0000

Data Index: 305276 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 1.6077. Min Range: -1.6077

Max Act: 0.8256. Min Act: -0.0000

Data Index: 985428 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 1.6077. Min Range: -1.6077

Max Act: 0.7736. Min Act: -0.0000

Data Index: 891650 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 1.6077. Min Range: -1.6077

Max Act: 0.8210. Min Act: -0.0000

Data Index: 336743 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 1.6077. Min Range: -1.6077

Max Act: 0.7572. Min Act: -0.0000

Data Index: 955751 (C4 (Web Text))

Max Activating Token Index: 61