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

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

Neuron 1513 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: 0.0744. Min Range: -0.0744

Max Act: 0.0744. Min Act: -0.0003

Data Index: 601774 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0739. Min Act: -0.0003

Data Index: 839063 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0734. Min Act: -0.0003

Data Index: 1355610 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0728. Min Act: -0.0003

Data Index: 805207 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0729. Min Act: -0.0003

Data Index: 1112986 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0709. Min Act: -0.0003

Data Index: 233479 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0715. Min Act: -0.0003

Data Index: 1257814 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0694. Min Act: -0.0003

Data Index: 488430 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0705. Min Act: -0.0004

Data Index: 199809 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0689. Min Act: -0.0004

Data Index: 986514 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0694. Min Act: -0.0004

Data Index: 782624 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0673. Min Act: -0.0004

Data Index: 219452 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0672. Min Act: -0.0003

Data Index: 669675 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0658. Min Act: -0.0003

Data Index: 123478 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0664. Min Act: -0.0003

Data Index: 857949 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0682. Min Act: -0.0003

Data Index: 557349 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0647. Min Act: -0.0003

Data Index: 983136 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0648. Min Act: -0.0003

Data Index: 657261 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0648. Min Act: -0.0003

Data Index: 105912 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0641. Min Act: -0.0003

Data Index: 1139664 (C4 (Web Text))

Max Activating Token Index: 281