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

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

Neuron 475 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.3722. Min Act: 0.0000

Data Index: 662520 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.3738. Min Act: -0.0000

Data Index: 416814 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.2985. Min Act: -0.0000

Data Index: 647177 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.3711. Min Act: -0.0000

Data Index: 980526 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.1500. Min Act: 0.0000

Data Index: 478085 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.0873. Min Act: -0.0000

Data Index: 345854 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.1611. Min Act: -0.0000

Data Index: 1307978 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.0745. Min Act: 0.0000

Data Index: 705617 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.0548. Min Act: -0.0000

Data Index: 1021229 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.0457. Min Act: -0.0000

Data Index: 498341 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.0288. Min Act: -0.0000

Data Index: 436508 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.0333. Min Act: -0.0000

Data Index: 351778 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 1.3738. Min Range: -1.3738

Max Act: 0.9818. Min Act: -0.0000

Data Index: 318579 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 1.3738. Min Range: -1.3738

Max Act: 0.9930. Min Act: 0.0000

Data Index: 703633 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 1.3738. Min Range: -1.3738

Max Act: 0.9783. Min Act: -0.0000

Data Index: 16873 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.0447. Min Act: -0.0000

Data Index: 498381 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 1.3738. Min Range: -1.3738

Max Act: 0.9845. Min Act: -0.0000

Data Index: 1320523 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 1.3738. Min Range: -1.3738

Max Act: 0.9590. Min Act: -0.0000

Data Index: 516390 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 1.3738. Min Range: -1.3738

Max Act: 0.9137. Min Act: -0.0000

Data Index: 718076 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 1.3738. Min Range: -1.3738

Max Act: 0.8983. Min Act: -0.0000

Data Index: 112018 (C4 (Web Text))

Max Activating Token Index: 660