Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1008 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0795. Min Act: -0.0005

Data Index: 1069225 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0769. Min Act: -0.0005

Data Index: 1182836 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0748. Min Act: -0.0005

Data Index: 1169013 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0739. Min Act: -0.0005

Data Index: 611753 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0724. Min Act: -0.0005

Data Index: 416037 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0659. Min Act: -0.0005

Data Index: 982205 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0715. Min Act: -0.0005

Data Index: 685914 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0651. Min Act: -0.0005

Data Index: 645072 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0638. Min Act: -0.0005

Data Index: 548738 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0561. Min Act: -0.0005

Data Index: 555069 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0557. Min Act: -0.0005

Data Index: 1559549 (Python Code)

Max Activating Token Index: 490

Text #11

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0505. Min Act: -0.0005

Data Index: 182757 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0524. Min Act: -0.0005

Data Index: 1546715 (Python Code)

Max Activating Token Index: 45

Text #13

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0511. Min Act: -0.0005

Data Index: 253641 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0516. Min Act: -0.0005

Data Index: 1598563 (Python Code)

Max Activating Token Index: 179

Text #15

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0487. Min Act: -0.0005

Data Index: 1497875 (Python Code)

Max Activating Token Index: 708

Text #16

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0470. Min Act: -0.0005

Data Index: 1208553 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0454. Min Act: -0.0005

Data Index: 432506 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0482. Min Act: -0.0005

Data Index: 506756 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0475. Min Act: -0.0005

Data Index: 233615 (C4 (Web Text))

Max Activating Token Index: 711