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

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

Neuron 4062 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: 1.9719. Min Range: -1.9719

Max Act: 1.9719. Min Act: -0.0000

Data Index: 735206 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.7361. Min Act: -0.0000

Data Index: 848842 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.4897. Min Act: -0.0000

Data Index: 774182 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.5173. Min Act: -0.0000

Data Index: 499649 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.3200. Min Act: -0.0000

Data Index: 981007 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.4634. Min Act: -0.0000

Data Index: 1246151 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.5559. Min Act: -0.0000

Data Index: 1170747 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.3969. Min Act: -0.0000

Data Index: 914086 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.3781. Min Act: -0.0000

Data Index: 622338 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.4014. Min Act: -0.0000

Data Index: 368264 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.3668. Min Act: -0.0000

Data Index: 561904 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.3580. Min Act: -0.0000

Data Index: 982210 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.4345. Min Act: -0.0000

Data Index: 151176 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.3353. Min Act: -0.0000

Data Index: 666229 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.3752. Min Act: -0.0000

Data Index: 1317961 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.4115. Min Act: -0.0000

Data Index: 714627 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.2837. Min Act: -0.0000

Data Index: 1234603 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.3231. Min Act: -0.0000

Data Index: 1302326 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.5195. Min Act: -0.0000

Data Index: 838686 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.3490. Min Act: -0.0000

Data Index: 1152706 (C4 (Web Text))

Max Activating Token Index: 485