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

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

Neuron 2096 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3718. Min Range: -3.3718

Max Act: 3.3718. Min Act: -0.0000

Data Index: 131937 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 3.3718. Min Range: -3.3718

Max Act: 2.7558. Min Act: -0.0000

Data Index: 426048 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 3.3718. Min Range: -3.3718

Max Act: 2.6387. Min Act: -0.0000

Data Index: 746661 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 3.3718. Min Range: -3.3718

Max Act: 2.6432. Min Act: -0.0000

Data Index: 1168946 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 3.3718. Min Range: -3.3718

Max Act: 2.3838. Min Act: -0.0000

Data Index: 734569 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 3.3718. Min Range: -3.3718

Max Act: 2.1752. Min Act: -0.0000

Data Index: 744870 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 3.3718. Min Range: -3.3718

Max Act: 2.3707. Min Act: -0.0000

Data Index: 858232 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 3.3718. Min Range: -3.3718

Max Act: 2.2376. Min Act: -0.0000

Data Index: 951130 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 3.3718. Min Range: -3.3718

Max Act: 2.0503. Min Act: -0.0000

Data Index: 363915 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 3.3718. Min Range: -3.3718

Max Act: 2.1083. Min Act: -0.0000

Data Index: 1161006 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 3.3718. Min Range: -3.3718

Max Act: 1.9369. Min Act: -0.0000

Data Index: 747234 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 3.3718. Min Range: -3.3718

Max Act: 1.9878. Min Act: -0.0000

Data Index: 370675 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 3.3718. Min Range: -3.3718

Max Act: 1.9165. Min Act: -0.0000

Data Index: 494401 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 3.3718. Min Range: -3.3718

Max Act: 1.9169. Min Act: -0.0000

Data Index: 1356974 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 3.3718. Min Range: -3.3718

Max Act: 1.8666. Min Act: -0.0000

Data Index: 80829 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 3.3718. Min Range: -3.3718

Max Act: 1.6465. Min Act: -0.0000

Data Index: 1165328 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 3.3718. Min Range: -3.3718

Max Act: 1.7289. Min Act: -0.0000

Data Index: 414691 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 3.3718. Min Range: -3.3718

Max Act: 1.7172. Min Act: -0.0000

Data Index: 701578 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 3.3718. Min Range: -3.3718

Max Act: 1.5963. Min Act: -0.0000

Data Index: 1248729 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 3.3718. Min Range: -3.3718

Max Act: 1.7194. Min Act: -0.0000

Data Index: 480241 (C4 (Web Text))

Max Activating Token Index: 571