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

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

Neuron 3274 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1074. Min Act: -0.0001

Data Index: 1174123 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0918. Min Act: -0.0001

Data Index: 699883 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0767. Min Act: -0.0002

Data Index: 1186165 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0789. Min Act: -0.0001

Data Index: 224971 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0862. Min Act: -0.0002

Data Index: 76347 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0782. Min Act: -0.0001

Data Index: 145573 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0750. Min Act: -0.0001

Data Index: 1289967 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0766. Min Act: -0.0001

Data Index: 1236150 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0720. Min Act: -0.0001

Data Index: 363262 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0683. Min Act: -0.0001

Data Index: 686006 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0737. Min Act: -0.0001

Data Index: 349905 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0770. Min Act: -0.0001

Data Index: 105551 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0715. Min Act: -0.0002

Data Index: 772417 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1084082 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0674. Min Act: -0.0001

Data Index: 65530 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0714. Min Act: -0.0001

Data Index: 1180830 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0708. Min Act: -0.0001

Data Index: 533096 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1047906 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0701. Min Act: -0.0001

Data Index: 308712 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0652. Min Act: -0.0001

Data Index: 671870 (C4 (Web Text))

Max Activating Token Index: 330