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

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

Neuron 1717 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: 0.0644. Min Range: -0.0644

Max Act: 0.0644. Min Act: -0.0003

Data Index: 1264163 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0612. Min Act: -0.0003

Data Index: 566530 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0574. Min Act: -0.0003

Data Index: 295942 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0610. Min Act: -0.0003

Data Index: 623557 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0571. Min Act: -0.0003

Data Index: 1573119 (Python Code)

Max Activating Token Index: 916

Text #5

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0587. Min Act: -0.0003

Data Index: 1654080 (Python Code)

Max Activating Token Index: 334

Text #6

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0600. Min Act: -0.0003

Data Index: 567169 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0572. Min Act: -0.0003

Data Index: 1309875 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0566. Min Act: -0.0003

Data Index: 711576 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0561. Min Act: -0.0003

Data Index: 777092 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0582. Min Act: -0.0003

Data Index: 230796 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0567. Min Act: -0.0003

Data Index: 1061469 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0561. Min Act: -0.0003

Data Index: 1153521 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0547. Min Act: -0.0003

Data Index: 973893 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0537. Min Act: -0.0003

Data Index: 1260567 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0510. Min Act: -0.0003

Data Index: 754273 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0536. Min Act: -0.0003

Data Index: 1171546 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0535. Min Act: -0.0003

Data Index: 1226618 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0548. Min Act: -0.0003

Data Index: 1488593 (Python Code)

Max Activating Token Index: 657

Text #19

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0508. Min Act: -0.0003

Data Index: 653541 (C4 (Web Text))

Max Activating Token Index: 961