Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3018 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0932. Min Act: -0.0002

Data Index: 916011 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.1040. Min Act: -0.0001

Data Index: 717895 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0763. Min Act: -0.0001

Data Index: 194925 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0782. Min Act: -0.0002

Data Index: 435557 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1148039 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0720. Min Act: -0.0001

Data Index: 897673 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0724. Min Act: -0.0001

Data Index: 801112 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0721. Min Act: -0.0002

Data Index: 392760 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0691. Min Act: -0.0001

Data Index: 89705 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0675. Min Act: -0.0002

Data Index: 575457 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1003027 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0651. Min Act: -0.0001

Data Index: 858710 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0661. Min Act: -0.0002

Data Index: 852519 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0671. Min Act: -0.0002

Data Index: 1086955 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1072200 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0663. Min Act: -0.0001

Data Index: 280950 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0673. Min Act: -0.0001

Data Index: 110759 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0607. Min Act: -0.0002

Data Index: 517746 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0658. Min Act: -0.0002

Data Index: 199851 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1133132 (C4 (Web Text))

Max Activating Token Index: 376