Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 146 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0726. Min Act: -0.0003

Data Index: 1166972 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0718. Min Act: -0.0003

Data Index: 650542 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0720. Min Act: -0.0003

Data Index: 103775 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0697. Min Act: -0.0003

Data Index: 67294 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1205920 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0691. Min Act: -0.0003

Data Index: 950090 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0656. Min Act: -0.0003

Data Index: 360505 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0614. Min Act: -0.0002

Data Index: 330895 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0629. Min Act: -0.0003

Data Index: 638854 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0651. Min Act: -0.0003

Data Index: 995481 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0626. Min Act: -0.0003

Data Index: 1081689 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0606. Min Act: -0.0003

Data Index: 989421 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0627. Min Act: -0.0003

Data Index: 525751 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0599. Min Act: -0.0003

Data Index: 1057143 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0605. Min Act: -0.0003

Data Index: 964642 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0607. Min Act: -0.0003

Data Index: 321861 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0592. Min Act: -0.0003

Data Index: 271025 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0598. Min Act: -0.0002

Data Index: 206816 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0589. Min Act: -0.0003

Data Index: 305889 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0593. Min Act: -0.0003

Data Index: 1355357 (C4 (Web Text))

Max Activating Token Index: 674