Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4108 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.8752. Min Act: -0.0000

Data Index: 757791 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.7931. Min Act: -0.0000

Data Index: 546462 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.7650. Min Act: -0.0000

Data Index: 450734 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1098398 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.8017. Min Act: -0.0000

Data Index: 618178 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.7995. Min Act: -0.0000

Data Index: 530120 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.7608. Min Act: -0.0000

Data Index: 704066 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.7506. Min Act: 0.0000

Data Index: 1018550 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.8025. Min Act: -0.0000

Data Index: 1318148 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6720. Min Act: -0.0000

Data Index: 626558 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.7122. Min Act: -0.0000

Data Index: 373677 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1220184 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6827. Min Act: -0.0000

Data Index: 292733 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6761. Min Act: -0.0000

Data Index: 1218278 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1327472 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6712. Min Act: -0.0000

Data Index: 871090 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6595. Min Act: -0.0000

Data Index: 486489 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6158. Min Act: -0.0000

Data Index: 25635 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6388. Min Act: -0.0000

Data Index: 181433 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6366. Min Act: -0.0000

Data Index: 986350 (C4 (Web Text))

Max Activating Token Index: 126