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

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

Neuron 3628 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1072. Min Range: -2.1072

Max Act: 2.0835. Min Act: -0.0000

Data Index: 1044402 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 2.1072. Min Range: -2.1072

Max Act: 2.0683. Min Act: -0.0000

Data Index: 88827 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 2.1072. Min Range: -2.1072

Max Act: 2.1072. Min Act: -0.0000

Data Index: 744942 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.8715. Min Act: -0.0000

Data Index: 138916 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.9140. Min Act: -0.0000

Data Index: 158063 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.7294. Min Act: -0.0000

Data Index: 896274 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.6207. Min Act: -0.0000

Data Index: 713459 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.6880. Min Act: -0.0000

Data Index: 1629332 (Python Code)

Max Activating Token Index: 744

Text #8

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.7766. Min Act: -0.0000

Data Index: 436877 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.7618. Min Act: -0.0000

Data Index: 1400223 (Python Code)

Max Activating Token Index: 687

Text #10

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.7612. Min Act: -0.0000

Data Index: 131243 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.8454. Min Act: -0.0000

Data Index: 1258330 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.7499. Min Act: -0.0000

Data Index: 891006 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.7351. Min Act: -0.0000

Data Index: 825411 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.7358. Min Act: -0.0000

Data Index: 1061709 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.6410. Min Act: -0.0000

Data Index: 838117 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.6367. Min Act: -0.0000

Data Index: 585783 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.7228. Min Act: -0.0000

Data Index: 832504 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.8079. Min Act: -0.0000

Data Index: 766412 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.6165. Min Act: -0.0000

Data Index: 1020499 (C4 (Web Text))

Max Activating Token Index: 123