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

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

Neuron 242 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: 0.0686. Min Range: -0.0686

Max Act: 0.0686. Min Act: -0.0003

Data Index: 14543 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0683. Min Act: -0.0003

Data Index: 1088168 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0652. Min Act: -0.0003

Data Index: 675347 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0618. Min Act: -0.0003

Data Index: 1272714 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0654. Min Act: -0.0003

Data Index: 378807 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0642. Min Act: -0.0004

Data Index: 568675 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0638. Min Act: -0.0003

Data Index: 1341524 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1325448 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0592. Min Act: -0.0003

Data Index: 1181315 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0574. Min Act: -0.0003

Data Index: 1252302 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0593. Min Act: -0.0003

Data Index: 418161 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0569. Min Act: -0.0003

Data Index: 821987 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0590. Min Act: -0.0003

Data Index: 903666 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0569. Min Act: -0.0003

Data Index: 113222 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0555. Min Act: -0.0002

Data Index: 635181 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0570. Min Act: -0.0004

Data Index: 28994 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0549. Min Act: -0.0003

Data Index: 1335864 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0559. Min Act: -0.0003

Data Index: 998080 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0559. Min Act: -0.0003

Data Index: 1086524 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0570. Min Act: -0.0003

Data Index: 388792 (C4 (Web Text))

Max Activating Token Index: 780