Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2782 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0980. Min Act: -0.0003

Data Index: 1245878 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0788. Min Act: -0.0003

Data Index: 585069 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0825. Min Act: -0.0003

Data Index: 184114 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0722. Min Act: -0.0003

Data Index: 509704 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0655. Min Act: -0.0003

Data Index: 943693 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0638. Min Act: -0.0003

Data Index: 1320900 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0638. Min Act: -0.0003

Data Index: 827106 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0651. Min Act: -0.0003

Data Index: 390998 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0613. Min Act: -0.0003

Data Index: 1126859 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0608. Min Act: -0.0003

Data Index: 1007712 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0586. Min Act: -0.0003

Data Index: 631945 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0585. Min Act: -0.0003

Data Index: 907300 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0568. Min Act: -0.0003

Data Index: 133383 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0576. Min Act: -0.0003

Data Index: 111009 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0572. Min Act: -0.0003

Data Index: 246244 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0560. Min Act: -0.0003

Data Index: 1174195 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0546. Min Act: -0.0003

Data Index: 1146867 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0574. Min Act: -0.0003

Data Index: 704018 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0571. Min Act: -0.0003

Data Index: 939371 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0557. Min Act: -0.0003

Data Index: 725556 (C4 (Web Text))

Max Activating Token Index: 531