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

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

Neuron 34 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: 2.3445. Min Range: -2.3445

Max Act: 2.3445. Min Act: -0.0000

Data Index: 129887 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 2.3445. Min Range: -2.3445

Max Act: 2.1879. Min Act: -0.0000

Data Index: 748263 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 2.3445. Min Range: -2.3445

Max Act: 2.0302. Min Act: -0.0000

Data Index: 1115223 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 2.3445. Min Range: -2.3445

Max Act: 1.9734. Min Act: -0.0000

Data Index: 628374 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 2.3445. Min Range: -2.3445

Max Act: 2.0840. Min Act: -0.0000

Data Index: 324578 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 2.3445. Min Range: -2.3445

Max Act: 2.0433. Min Act: -0.0000

Data Index: 684376 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 2.3445. Min Range: -2.3445

Max Act: 1.9071. Min Act: -0.0000

Data Index: 576349 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 2.3445. Min Range: -2.3445

Max Act: 1.8663. Min Act: -0.0000

Data Index: 360958 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 2.3445. Min Range: -2.3445

Max Act: 1.9649. Min Act: -0.0000

Data Index: 1178527 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 2.3445. Min Range: -2.3445

Max Act: 1.9464. Min Act: -0.0000

Data Index: 671984 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 2.3445. Min Range: -2.3445

Max Act: 1.8560. Min Act: -0.0000

Data Index: 519748 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 2.3445. Min Range: -2.3445

Max Act: 1.8558. Min Act: -0.0000

Data Index: 193171 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 2.3445. Min Range: -2.3445

Max Act: 1.8483. Min Act: -0.0000

Data Index: 989674 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 2.3445. Min Range: -2.3445

Max Act: 2.0581. Min Act: -0.0000

Data Index: 627007 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 2.3445. Min Range: -2.3445

Max Act: 1.7395. Min Act: -0.0000

Data Index: 1007070 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 2.3445. Min Range: -2.3445

Max Act: 1.7624. Min Act: -0.0000

Data Index: 1147146 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 2.3445. Min Range: -2.3445

Max Act: 1.6479. Min Act: -0.0000

Data Index: 364486 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 2.3445. Min Range: -2.3445

Max Act: 1.6382. Min Act: -0.0000

Data Index: 1098769 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 2.3445. Min Range: -2.3445

Max Act: 1.6595. Min Act: -0.0000

Data Index: 346586 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 2.3445. Min Range: -2.3445

Max Act: 1.6736. Min Act: -0.0000

Data Index: 961422 (C4 (Web Text))

Max Activating Token Index: 307