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

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

Neuron 94 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: 2.5667. Min Range: -2.5667

Max Act: 2.5667. Min Act: -0.0000

Data Index: 931381 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 2.5667. Min Range: -2.5667

Max Act: 2.2932. Min Act: -0.0000

Data Index: 577341 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 2.5667. Min Range: -2.5667

Max Act: 2.1470. Min Act: -0.0000

Data Index: 244175 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 2.5667. Min Range: -2.5667

Max Act: 2.1025. Min Act: -0.0000

Data Index: 653163 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 2.5667. Min Range: -2.5667

Max Act: 2.0906. Min Act: -0.0000

Data Index: 274146 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 2.5667. Min Range: -2.5667

Max Act: 1.9442. Min Act: -0.0000

Data Index: 253758 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 2.5667. Min Range: -2.5667

Max Act: 2.0385. Min Act: -0.0000

Data Index: 942280 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 2.5667. Min Range: -2.5667

Max Act: 1.9626. Min Act: -0.0000

Data Index: 192178 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 2.5667. Min Range: -2.5667

Max Act: 2.1057. Min Act: -0.0000

Data Index: 215079 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 2.5667. Min Range: -2.5667

Max Act: 2.1002. Min Act: -0.0000

Data Index: 124809 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 2.5667. Min Range: -2.5667

Max Act: 1.9074. Min Act: -0.0000

Data Index: 1215828 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 2.5667. Min Range: -2.5667

Max Act: 1.8709. Min Act: -0.0000

Data Index: 814783 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 2.5667. Min Range: -2.5667

Max Act: 1.8580. Min Act: -0.0000

Data Index: 959744 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 2.5667. Min Range: -2.5667

Max Act: 1.7839. Min Act: -0.0000

Data Index: 508267 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 2.5667. Min Range: -2.5667

Max Act: 2.0077. Min Act: -0.0000

Data Index: 278343 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 2.5667. Min Range: -2.5667

Max Act: 1.8654. Min Act: -0.0000

Data Index: 632541 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 2.5667. Min Range: -2.5667

Max Act: 1.9475. Min Act: -0.0000

Data Index: 1196127 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 2.5667. Min Range: -2.5667

Max Act: 1.7785. Min Act: -0.0000

Data Index: 521739 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 2.5667. Min Range: -2.5667

Max Act: 1.8730. Min Act: -0.0000

Data Index: 1171137 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 2.5667. Min Range: -2.5667

Max Act: 1.8749. Min Act: -0.0000

Data Index: 386203 (C4 (Web Text))

Max Activating Token Index: 862