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

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

Neuron 1146 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.9415. Min Act: -0.0000

Data Index: 136702 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.9893. Min Act: -0.0000

Data Index: 243934 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.9409. Min Act: -0.0000

Data Index: 960821 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.9289. Min Act: 0.0001

Data Index: 467646 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.9087. Min Act: -0.0000

Data Index: 514407 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8697. Min Act: -0.0000

Data Index: 909322 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.9235. Min Act: -0.0000

Data Index: 503551 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8475. Min Act: -0.0000

Data Index: 149507 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8875. Min Act: -0.0000

Data Index: 340080 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8873. Min Act: -0.0000

Data Index: 570452 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8273. Min Act: -0.0000

Data Index: 176760 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8849. Min Act: -0.0000

Data Index: 558271 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8451. Min Act: 0.0000

Data Index: 1075621 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8635. Min Act: -0.0000

Data Index: 461383 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8038. Min Act: -0.0000

Data Index: 101549 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.7911. Min Act: -0.0000

Data Index: 1014252 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.7851. Min Act: -0.0000

Data Index: 1348235 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.7834. Min Act: -0.0000

Data Index: 153486 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8047. Min Act: -0.0000

Data Index: 1104357 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.7743. Min Act: -0.0000

Data Index: 66896 (C4 (Web Text))

Max Activating Token Index: 185