Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2570 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0695. Min Act: -0.0004

Data Index: 866158 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0642. Min Act: -0.0004

Data Index: 871713 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0550. Min Act: -0.0004

Data Index: 122740 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0550. Min Act: -0.0004

Data Index: 1234308 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0521. Min Act: -0.0004

Data Index: 1178081 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0540. Min Act: -0.0004

Data Index: 1074129 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0540. Min Act: -0.0004

Data Index: 1070285 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0510. Min Act: -0.0004

Data Index: 860148 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0507. Min Act: -0.0004

Data Index: 124908 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0515. Min Act: -0.0004

Data Index: 691115 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0514. Min Act: -0.0004

Data Index: 617385 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0564. Min Act: -0.0004

Data Index: 473190 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0552. Min Act: -0.0004

Data Index: 949108 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0529. Min Act: -0.0004

Data Index: 428380 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0519. Min Act: -0.0004

Data Index: 1241994 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0468. Min Act: -0.0004

Data Index: 144017 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0563. Min Act: -0.0004

Data Index: 935902 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0521. Min Act: -0.0004

Data Index: 366746 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0444. Min Act: -0.0004

Data Index: 445082 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0549. Min Act: -0.0004

Data Index: 1116232 (C4 (Web Text))

Max Activating Token Index: 255