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

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

Neuron 2900 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.9797. Min Act: -0.0002

Data Index: 788678 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8533. Min Act: -0.0002

Data Index: 226289 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8087. Min Act: -0.0002

Data Index: 749031 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7786. Min Act: -0.0002

Data Index: 808746 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7410. Min Act: -0.0002

Data Index: 1222576 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7365. Min Act: -0.0002

Data Index: 1296944 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7430. Min Act: -0.0002

Data Index: 214341 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7211. Min Act: -0.0002

Data Index: 688025 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7105. Min Act: -0.0002

Data Index: 988995 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7318. Min Act: -0.0002

Data Index: 1087591 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6845. Min Act: -0.0002

Data Index: 42905 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7012. Min Act: -0.0002

Data Index: 964740 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6781. Min Act: -0.0002

Data Index: 899607 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6765. Min Act: -0.0002

Data Index: 260765 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6832. Min Act: -0.0002

Data Index: 225280 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6992. Min Act: -0.0002

Data Index: 1289802 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6759. Min Act: -0.0002

Data Index: 510230 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6653. Min Act: -0.0002

Data Index: 862995 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6832. Min Act: -0.0002

Data Index: 153106 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6587. Min Act: -0.0002

Data Index: 558921 (C4 (Web Text))

Max Activating Token Index: 174