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

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

Neuron 3082 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0847. Min Act: -0.0002

Data Index: 1055430 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0833. Min Act: -0.0002

Data Index: 469082 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1039630 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0803. Min Act: -0.0002

Data Index: 6721 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0749. Min Act: -0.0002

Data Index: 613308 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0708. Min Act: -0.0002

Data Index: 128178 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0673. Min Act: -0.0002

Data Index: 527558 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0732. Min Act: -0.0002

Data Index: 209913 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0755. Min Act: -0.0002

Data Index: 261653 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0746. Min Act: -0.0002

Data Index: 254588 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0712. Min Act: -0.0002

Data Index: 562773 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0670. Min Act: -0.0002

Data Index: 928637 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0702. Min Act: -0.0002

Data Index: 638675 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0697. Min Act: -0.0002

Data Index: 1094468 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0714. Min Act: -0.0002

Data Index: 814411 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0690. Min Act: -0.0002

Data Index: 509372 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0704. Min Act: -0.0002

Data Index: 725694 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0681. Min Act: -0.0002

Data Index: 88930 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0662. Min Act: -0.0002

Data Index: 838703 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0656. Min Act: -0.0002

Data Index: 90117 (C4 (Web Text))

Max Activating Token Index: 291