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

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

Neuron 4101 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4280. Min Range: -2.4280

Max Act: 2.4280. Min Act: -0.0000

Data Index: 454562 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 2.4280. Min Range: -2.4280

Max Act: 2.2963. Min Act: -0.0000

Data Index: 1149172 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 2.4280. Min Range: -2.4280

Max Act: 1.9388. Min Act: -0.0000

Data Index: 61496 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 2.4280. Min Range: -2.4280

Max Act: 1.7917. Min Act: -0.0000

Data Index: 416941 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 2.4280. Min Range: -2.4280

Max Act: 1.6349. Min Act: -0.0000

Data Index: 961094 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 2.4280. Min Range: -2.4280

Max Act: 1.5917. Min Act: -0.0000

Data Index: 1571415 (Python Code)

Max Activating Token Index: 941

Text #6

Max Range: 2.4280. Min Range: -2.4280

Max Act: 1.6247. Min Act: -0.0000

Data Index: 1087960 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 2.4280. Min Range: -2.4280

Max Act: 1.5885. Min Act: -0.0000

Data Index: 1182137 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 2.4280. Min Range: -2.4280

Max Act: 1.4930. Min Act: -0.0000

Data Index: 1492619 (Python Code)

Max Activating Token Index: 463

Text #9

Max Range: 2.4280. Min Range: -2.4280

Max Act: 1.4794. Min Act: -0.0000

Data Index: 719654 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 2.4280. Min Range: -2.4280

Max Act: 1.5627. Min Act: -0.0000

Data Index: 523052 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 2.4280. Min Range: -2.4280

Max Act: 1.5707. Min Act: -0.0000

Data Index: 1025897 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 2.4280. Min Range: -2.4280

Max Act: 1.5130. Min Act: -0.0000

Data Index: 1113802 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 2.4280. Min Range: -2.4280

Max Act: 1.4915. Min Act: -0.0000

Data Index: 1466172 (Python Code)

Max Activating Token Index: 113

Text #14

Max Range: 2.4280. Min Range: -2.4280

Max Act: 1.4847. Min Act: -0.0000

Data Index: 540736 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 2.4280. Min Range: -2.4280

Max Act: 1.5202. Min Act: -0.0000

Data Index: 1433122 (Python Code)

Max Activating Token Index: 832

Text #16

Max Range: 2.4280. Min Range: -2.4280

Max Act: 1.4785. Min Act: -0.0000

Data Index: 584759 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 2.4280. Min Range: -2.4280

Max Act: 1.5217. Min Act: -0.0000

Data Index: 1187863 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 2.4280. Min Range: -2.4280

Max Act: 1.4283. Min Act: -0.0000

Data Index: 231937 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 2.4280. Min Range: -2.4280

Max Act: 1.4105. Min Act: -0.0000

Data Index: 726806 (C4 (Web Text))

Max Activating Token Index: 402