Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2198 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8088. Min Range: -1.8088

Max Act: 1.7936. Min Act: -0.0001

Data Index: 650225 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 1.8088. Min Range: -1.8088

Max Act: 1.8088. Min Act: -0.0001

Data Index: 416782 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 1.8088. Min Range: -1.8088

Max Act: 1.7523. Min Act: -0.0001

Data Index: 459879 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 1.8088. Min Range: -1.8088

Max Act: 1.6959. Min Act: -0.0001

Data Index: 706460 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 1.8088. Min Range: -1.8088

Max Act: 1.5862. Min Act: -0.0001

Data Index: 1291144 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 1.8088. Min Range: -1.8088

Max Act: 1.4008. Min Act: -0.0001

Data Index: 950738 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 1.8088. Min Range: -1.8088

Max Act: 1.6553. Min Act: -0.0001

Data Index: 1304835 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 1.8088. Min Range: -1.8088

Max Act: 1.6308. Min Act: -0.0001

Data Index: 449720 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 1.8088. Min Range: -1.8088

Max Act: 1.5497. Min Act: -0.0001

Data Index: 904222 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 1.8088. Min Range: -1.8088

Max Act: 1.6383. Min Act: -0.0001

Data Index: 999833 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 1.8088. Min Range: -1.8088

Max Act: 1.5678. Min Act: -0.0001

Data Index: 572512 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 1.8088. Min Range: -1.8088

Max Act: 1.6275. Min Act: -0.0001

Data Index: 1336042 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 1.8088. Min Range: -1.8088

Max Act: 1.6098. Min Act: -0.0001

Data Index: 845855 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 1.8088. Min Range: -1.8088

Max Act: 1.5782. Min Act: -0.0001

Data Index: 1045556 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 1.8088. Min Range: -1.8088

Max Act: 1.6068. Min Act: -0.0001

Data Index: 919959 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 1.8088. Min Range: -1.8088

Max Act: 1.5483. Min Act: -0.0001

Data Index: 147752 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 1.8088. Min Range: -1.8088

Max Act: 1.5368. Min Act: -0.0001

Data Index: 1061137 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 1.8088. Min Range: -1.8088

Max Act: 1.5939. Min Act: -0.0001

Data Index: 280683 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 1.8088. Min Range: -1.8088

Max Act: 1.4617. Min Act: -0.0001

Data Index: 493502 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 1.8088. Min Range: -1.8088

Max Act: 1.5063. Min Act: -0.0001

Data Index: 667844 (C4 (Web Text))

Max Activating Token Index: 109