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

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

Neuron 4069 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5653. Min Range: -2.5653

Max Act: 2.3031. Min Act: -0.0000

Data Index: 234131 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 2.5653. Min Range: -2.5653

Max Act: 2.3010. Min Act: -0.0000

Data Index: 279273 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 2.5653. Min Range: -2.5653

Max Act: 2.5653. Min Act: -0.0000

Data Index: 463470 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 2.5653. Min Range: -2.5653

Max Act: 2.2816. Min Act: -0.0000

Data Index: 12889 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 2.5653. Min Range: -2.5653

Max Act: 2.2779. Min Act: -0.0000

Data Index: 1209065 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 2.5653. Min Range: -2.5653

Max Act: 2.2111. Min Act: -0.0000

Data Index: 687561 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 2.5653. Min Range: -2.5653

Max Act: 1.9511. Min Act: -0.0000

Data Index: 628645 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 2.5653. Min Range: -2.5653

Max Act: 2.0487. Min Act: -0.0000

Data Index: 927259 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 2.5653. Min Range: -2.5653

Max Act: 2.2716. Min Act: -0.0000

Data Index: 1319177 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 2.5653. Min Range: -2.5653

Max Act: 2.0113. Min Act: -0.0000

Data Index: 52952 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 2.5653. Min Range: -2.5653

Max Act: 1.9367. Min Act: -0.0000

Data Index: 453782 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 2.5653. Min Range: -2.5653

Max Act: 1.9731. Min Act: -0.0000

Data Index: 951522 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 2.5653. Min Range: -2.5653

Max Act: 1.8240. Min Act: -0.0000

Data Index: 350372 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 2.5653. Min Range: -2.5653

Max Act: 1.7126. Min Act: -0.0000

Data Index: 149121 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 2.5653. Min Range: -2.5653

Max Act: 1.9550. Min Act: -0.0000

Data Index: 983074 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 2.5653. Min Range: -2.5653

Max Act: 1.8222. Min Act: -0.0000

Data Index: 600357 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 2.5653. Min Range: -2.5653

Max Act: 1.8123. Min Act: -0.0000

Data Index: 888997 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 2.5653. Min Range: -2.5653

Max Act: 2.0440. Min Act: -0.0000

Data Index: 239005 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 2.5653. Min Range: -2.5653

Max Act: 1.7702. Min Act: -0.0000

Data Index: 1229937 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 2.5653. Min Range: -2.5653

Max Act: 1.8942. Min Act: -0.0000

Data Index: 460181 (C4 (Web Text))

Max Activating Token Index: 753