Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2719 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.4358. Min Act: -0.0000

Data Index: 89429 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.4556. Min Act: -0.0000

Data Index: 421815 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.4314. Min Act: -0.0000

Data Index: 60827 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.4167. Min Act: -0.0000

Data Index: 99281 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.4008. Min Act: -0.0000

Data Index: 322555 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.4114. Min Act: -0.0000

Data Index: 23684 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.3942. Min Act: -0.0000

Data Index: 490148 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.4047. Min Act: -0.0000

Data Index: 51807 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.3857. Min Act: -0.0000

Data Index: 652856 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.3719. Min Act: -0.0000

Data Index: 506986 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.3915. Min Act: -0.0000

Data Index: 432467 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.3648. Min Act: -0.0000

Data Index: 271449 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.3737. Min Act: -0.0000

Data Index: 570143 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.3515. Min Act: -0.0000

Data Index: 755366 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.3699. Min Act: -0.0000

Data Index: 659767 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.3779. Min Act: -0.0000

Data Index: 850307 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.3598. Min Act: -0.0000

Data Index: 517378 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.3349. Min Act: -0.0000

Data Index: 818835 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.3891. Min Act: -0.0000

Data Index: 198970 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 0.4556. Min Range: -0.4556

Max Act: 0.3620. Min Act: -0.0000

Data Index: 634130 (C4 (Web Text))

Max Activating Token Index: 669