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

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

Neuron 1836 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0733. Min Range: -1.0733

Max Act: 1.0733. Min Act: -0.0000

Data Index: 180620 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 1.0733. Min Range: -1.0733

Max Act: 1.0256. Min Act: -0.0000

Data Index: 408642 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.6335. Min Act: -0.0000

Data Index: 315044 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.6424. Min Act: -0.0000

Data Index: 373098 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.6010. Min Act: -0.0000

Data Index: 869909 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.5790. Min Act: -0.0000

Data Index: 1396944 (Python Code)

Max Activating Token Index: 636

Text #6

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.5442. Min Act: -0.0000

Data Index: 108628 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.5009. Min Act: -0.0000

Data Index: 1256414 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.4847. Min Act: -0.0000

Data Index: 993291 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.4999. Min Act: -0.0000

Data Index: 586765 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.4869. Min Act: -0.0000

Data Index: 282006 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.4799. Min Act: -0.0000

Data Index: 413911 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.4531. Min Act: -0.0000

Data Index: 1028940 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.4484. Min Act: -0.0000

Data Index: 766484 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.4673. Min Act: -0.0000

Data Index: 71713 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.4175. Min Act: -0.0000

Data Index: 132281 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.4558. Min Act: -0.0000

Data Index: 9474 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.4352. Min Act: -0.0000

Data Index: 266530 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.4473. Min Act: -0.0000

Data Index: 1276364 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.4090. Min Act: -0.0000

Data Index: 709154 (C4 (Web Text))

Max Activating Token Index: 565