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

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

Neuron 5683 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6662. Min Act: -0.0000

Data Index: 784647 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6689. Min Act: -0.0000

Data Index: 686669 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6001. Min Act: -0.0000

Data Index: 1121216 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5567. Min Act: -0.0000

Data Index: 228929 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5368. Min Act: -0.0000

Data Index: 947298 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5441. Min Act: -0.0000

Data Index: 736680 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5053. Min Act: -0.0000

Data Index: 1243709 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5029. Min Act: -0.0000

Data Index: 932159 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4882. Min Act: -0.0000

Data Index: 1157971 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4712. Min Act: -0.0000

Data Index: 34054 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4839. Min Act: -0.0000

Data Index: 728272 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4815. Min Act: -0.0000

Data Index: 919316 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4827. Min Act: -0.0000

Data Index: 606968 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4817. Min Act: -0.0000

Data Index: 283619 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1023177 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5053. Min Act: -0.0000

Data Index: 480577 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4737. Min Act: -0.0000

Data Index: 1265127 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4746. Min Act: -0.0000

Data Index: 192745 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4652. Min Act: -0.0000

Data Index: 1229463 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4484. Min Act: -0.0000

Data Index: 1292430 (C4 (Web Text))

Max Activating Token Index: 555