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

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

Neuron 22 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.7026. Min Act: -0.0000

Data Index: 1309267 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.6534. Min Act: -0.0000

Data Index: 369084 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.5670. Min Act: -0.0000

Data Index: 269224 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.5838. Min Act: -0.0000

Data Index: 956141 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4854. Min Act: -0.0000

Data Index: 945476 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4683. Min Act: -0.0000

Data Index: 1279915 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4695. Min Act: -0.0000

Data Index: 600855 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4144. Min Act: -0.0000

Data Index: 593584 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4388. Min Act: -0.0000

Data Index: 437126 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4376. Min Act: -0.0000

Data Index: 195915 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4453. Min Act: -0.0000

Data Index: 464929 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4177. Min Act: -0.0000

Data Index: 494643 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4044. Min Act: -0.0000

Data Index: 177194 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.3895. Min Act: -0.0000

Data Index: 887586 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.3868. Min Act: -0.0000

Data Index: 743238 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.3972. Min Act: -0.0000

Data Index: 859799 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4007. Min Act: -0.0000

Data Index: 529876 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4020. Min Act: -0.0000

Data Index: 1063526 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.3808. Min Act: -0.0000

Data Index: 72488 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.3908. Min Act: -0.0000

Data Index: 634326 (C4 (Web Text))

Max Activating Token Index: 485