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

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

Neuron 3204 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.8720. Min Act: -0.0000

Data Index: 854653 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.6373. Min Act: -0.0000

Data Index: 823594 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.6271. Min Act: -0.0000

Data Index: 325447 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.6008. Min Act: -0.0000

Data Index: 609377 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.5648. Min Act: -0.0000

Data Index: 337868 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.5938. Min Act: -0.0000

Data Index: 756737 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.5727. Min Act: -0.0000

Data Index: 255745 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.5708. Min Act: -0.0000

Data Index: 581810 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.5468. Min Act: -0.0000

Data Index: 166454 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1113531 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.5409. Min Act: -0.0000

Data Index: 422852 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.5261. Min Act: -0.0000

Data Index: 755770 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.4954. Min Act: -0.0000

Data Index: 460251 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.5321. Min Act: -0.0000

Data Index: 745445 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.4986. Min Act: -0.0000

Data Index: 406801 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.5084. Min Act: -0.0000

Data Index: 474055 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.4890. Min Act: -0.0000

Data Index: 601297 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.4525. Min Act: -0.0000

Data Index: 858612 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.4802. Min Act: -0.0000

Data Index: 1083591 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.4935. Min Act: -0.0000

Data Index: 662323 (C4 (Web Text))

Max Activating Token Index: 44