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

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

Neuron 2001 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9067. Min Range: -1.9067

Max Act: 1.9067. Min Act: -0.0001

Data Index: 995332 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 1.9067. Min Range: -1.9067

Max Act: 1.4357. Min Act: -0.0001

Data Index: 897883 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 1.9067. Min Range: -1.9067

Max Act: 1.1716. Min Act: -0.0001

Data Index: 1306615 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 1.9067. Min Range: -1.9067

Max Act: 1.0287. Min Act: -0.0001

Data Index: 725979 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 1.9067. Min Range: -1.9067

Max Act: 1.0193. Min Act: -0.0001

Data Index: 334487 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 1.9067. Min Range: -1.9067

Max Act: 0.9857. Min Act: -0.0001

Data Index: 1136412 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 1.9067. Min Range: -1.9067

Max Act: 0.9544. Min Act: -0.0001

Data Index: 712296 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 1.9067. Min Range: -1.9067

Max Act: 0.9533. Min Act: -0.0001

Data Index: 536608 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 1.9067. Min Range: -1.9067

Max Act: 0.9633. Min Act: -0.0001

Data Index: 783024 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 1.9067. Min Range: -1.9067

Max Act: 0.8718. Min Act: -0.0001

Data Index: 594187 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 1.9067. Min Range: -1.9067

Max Act: 0.8332. Min Act: -0.0001

Data Index: 1280832 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 1.9067. Min Range: -1.9067

Max Act: 0.8311. Min Act: -0.0001

Data Index: 429106 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 1.9067. Min Range: -1.9067

Max Act: 0.9339. Min Act: -0.0001

Data Index: 643771 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 1.9067. Min Range: -1.9067

Max Act: 0.7659. Min Act: -0.0001

Data Index: 425824 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 1.9067. Min Range: -1.9067

Max Act: 0.6559. Min Act: -0.0001

Data Index: 798788 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 1.9067. Min Range: -1.9067

Max Act: 0.8186. Min Act: -0.0001

Data Index: 933484 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 1.9067. Min Range: -1.9067

Max Act: 0.7867. Min Act: -0.0001

Data Index: 729612 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 1.9067. Min Range: -1.9067

Max Act: 0.7634. Min Act: -0.0001

Data Index: 531402 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 1.9067. Min Range: -1.9067

Max Act: 0.8059. Min Act: -0.0001

Data Index: 540381 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 1.9067. Min Range: -1.9067

Max Act: 0.7396. Min Act: -0.0001

Data Index: 1149479 (C4 (Web Text))

Max Activating Token Index: 130