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

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

Neuron 2566 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0507. Min Act: -0.0002

Data Index: 586928 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1176109 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0388. Min Act: -0.0002

Data Index: 917655 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0357. Min Act: -0.0002

Data Index: 58709 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0420. Min Act: -0.0002

Data Index: 439295 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1091106 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1019253 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1249529 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0368. Min Act: -0.0002

Data Index: 83972 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0388. Min Act: -0.0002

Data Index: 737019 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0349. Min Act: -0.0002

Data Index: 740817 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0441. Min Act: -0.0002

Data Index: 250103 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1293530 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0394. Min Act: -0.0002

Data Index: 284054 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0390. Min Act: -0.0002

Data Index: 173067 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0360. Min Act: -0.0002

Data Index: 379466 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1074017 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0321. Min Act: -0.0002

Data Index: 377036 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1335452 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0403. Min Act: -0.0002

Data Index: 198327 (C4 (Web Text))

Max Activating Token Index: 8