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

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

Neuron 1577 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: 0.0864. Min Range: -0.0864

Max Act: 0.0864. Min Act: -0.0003

Data Index: 1216612 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0799. Min Act: -0.0003

Data Index: 49561 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0771. Min Act: -0.0003

Data Index: 1153757 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0741. Min Act: -0.0003

Data Index: 711819 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0701. Min Act: -0.0003

Data Index: 707356 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0702. Min Act: -0.0003

Data Index: 976086 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0705. Min Act: -0.0003

Data Index: 730343 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0675. Min Act: -0.0003

Data Index: 1048557 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0660. Min Act: -0.0003

Data Index: 1102324 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0650. Min Act: -0.0003

Data Index: 712549 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0668. Min Act: -0.0004

Data Index: 1189476 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0676. Min Act: -0.0004

Data Index: 111734 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0646. Min Act: -0.0003

Data Index: 1299541 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0650. Min Act: -0.0003

Data Index: 789852 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0653. Min Act: -0.0003

Data Index: 295438 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0636. Min Act: -0.0003

Data Index: 295610 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0651. Min Act: -0.0003

Data Index: 1114117 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0646. Min Act: -0.0003

Data Index: 951523 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1172246 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0636. Min Act: -0.0003

Data Index: 353140 (C4 (Web Text))

Max Activating Token Index: 399