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

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

Neuron 47 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.6821. Min Act: -0.0000

Data Index: 379763 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.5590. Min Act: -0.0000

Data Index: 621298 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4501. Min Act: -0.0000

Data Index: 569051 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.5538. Min Act: -0.0000

Data Index: 154437 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.5240. Min Act: -0.0000

Data Index: 816877 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4551. Min Act: -0.0000

Data Index: 840623 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4233. Min Act: -0.0000

Data Index: 554248 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4158. Min Act: -0.0000

Data Index: 1255342 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.3850. Min Act: -0.0000

Data Index: 822164 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4000. Min Act: -0.0000

Data Index: 584908 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1635594 (Python Code)

Max Activating Token Index: 380

Text #11

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.3096. Min Act: -0.0000

Data Index: 563582 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.3513. Min Act: -0.0000

Data Index: 692575 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.3294. Min Act: -0.0000

Data Index: 410748 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.3750. Min Act: -0.0000

Data Index: 166742 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.3443. Min Act: -0.0000

Data Index: 832788 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.3366. Min Act: -0.0000

Data Index: 241826 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.2680. Min Act: -0.0000

Data Index: 18370 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.3245. Min Act: -0.0000

Data Index: 1329699 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.2695. Min Act: -0.0000

Data Index: 824240 (C4 (Web Text))

Max Activating Token Index: 666