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

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

Neuron 4617 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: 1.0929. Min Range: -1.0929

Max Act: 1.0929. Min Act: -0.0002

Data Index: 1147786 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.9748. Min Act: -0.0002

Data Index: 337549 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.8423. Min Act: -0.0002

Data Index: 607367 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.8907. Min Act: -0.0002

Data Index: 25056 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.9676. Min Act: -0.0002

Data Index: 334781 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.8385. Min Act: -0.0002

Data Index: 1340736 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.8623. Min Act: -0.0002

Data Index: 798251 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.8396. Min Act: -0.0002

Data Index: 973109 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.8632. Min Act: -0.0002

Data Index: 940855 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.8533. Min Act: -0.0002

Data Index: 765638 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.8955. Min Act: -0.0002

Data Index: 1190125 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.8156. Min Act: -0.0002

Data Index: 1331503 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.8686. Min Act: -0.0002

Data Index: 603844 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.9507. Min Act: -0.0002

Data Index: 642527 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.8711. Min Act: -0.0002

Data Index: 1138403 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.8587. Min Act: -0.0002

Data Index: 332298 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.8786. Min Act: -0.0002

Data Index: 786263 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.8502. Min Act: -0.0002

Data Index: 638253 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.6805. Min Act: -0.0002

Data Index: 1215790 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.8014. Min Act: -0.0002

Data Index: 648322 (C4 (Web Text))

Max Activating Token Index: 700