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

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

Neuron 5001 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.6458. Min Act: -0.0001

Data Index: 587173 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.6647. Min Act: -0.0001

Data Index: 30179 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.6541. Min Act: -0.0001

Data Index: 1048890 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.6521. Min Act: -0.0001

Data Index: 479387 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.5648. Min Act: -0.0001

Data Index: 513751 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.6088. Min Act: -0.0001

Data Index: 461481 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.5947. Min Act: -0.0001

Data Index: 302508 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.5589. Min Act: -0.0001

Data Index: 1264692 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.5893. Min Act: -0.0001

Data Index: 676009 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.5543. Min Act: -0.0001

Data Index: 128654 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.5558. Min Act: -0.0001

Data Index: 472237 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.5796. Min Act: -0.0001

Data Index: 582055 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.5793. Min Act: -0.0001

Data Index: 1051229 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.5380. Min Act: -0.0001

Data Index: 910027 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.5525. Min Act: -0.0001

Data Index: 466779 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.5758. Min Act: -0.0001

Data Index: 925639 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.5527. Min Act: -0.0001

Data Index: 846873 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.5326. Min Act: -0.0001

Data Index: 1270556 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.5697. Min Act: -0.0001

Data Index: 1175018 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.5593. Min Act: -0.0001

Data Index: 167651 (C4 (Web Text))

Max Activating Token Index: 604