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

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

Neuron 5693 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: 0.7885. Min Range: -0.7885

Max Act: 0.7401. Min Act: -0.0000

Data Index: 360138 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.7885. Min Act: -0.0000

Data Index: 950677 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.7098. Min Act: -0.0000

Data Index: 811634 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1177680 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5482. Min Act: -0.0000

Data Index: 1111994 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1202696 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5209. Min Act: -0.0000

Data Index: 1190504 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5067. Min Act: 0.0000

Data Index: 391501 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5028. Min Act: -0.0000

Data Index: 245828 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4893. Min Act: -0.0000

Data Index: 487267 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5009. Min Act: -0.0000

Data Index: 1135663 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4918. Min Act: -0.0000

Data Index: 419991 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4646. Min Act: -0.0000

Data Index: 767073 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4651. Min Act: -0.0000

Data Index: 103157 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4737. Min Act: -0.0000

Data Index: 568918 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4513. Min Act: -0.0000

Data Index: 445795 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4664. Min Act: -0.0000

Data Index: 113863 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4634. Min Act: -0.0000

Data Index: 1292798 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4530. Min Act: -0.0000

Data Index: 207238 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4539. Min Act: -0.0000

Data Index: 310940 (C4 (Web Text))

Max Activating Token Index: 745