Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2775 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0704. Min Act: -0.0001

Data Index: 1260669 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0691. Min Act: -0.0001

Data Index: 725379 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0689. Min Act: -0.0001

Data Index: 1296835 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0634. Min Act: -0.0001

Data Index: 919721 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0638. Min Act: -0.0001

Data Index: 595892 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0599. Min Act: -0.0001

Data Index: 512112 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0573. Min Act: -0.0001

Data Index: 71653 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1120002 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0561. Min Act: -0.0001

Data Index: 577376 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1291008 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0529. Min Act: -0.0001

Data Index: 598935 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0569. Min Act: -0.0000

Data Index: 796438 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0582. Min Act: -0.0001

Data Index: 984387 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0560. Min Act: -0.0001

Data Index: 657896 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0581. Min Act: -0.0001

Data Index: 315836 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0532. Min Act: -0.0001

Data Index: 382019 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1321751 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0548. Min Act: -0.0001

Data Index: 1358189 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0508. Min Act: -0.0001

Data Index: 366972 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0542. Min Act: -0.0001

Data Index: 322255 (C4 (Web Text))

Max Activating Token Index: 144