Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1558 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0670. Min Act: -0.0002

Data Index: 885532 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0664. Min Act: -0.0002

Data Index: 62871 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0601. Min Act: -0.0002

Data Index: 368854 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0614. Min Act: -0.0001

Data Index: 597830 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0581. Min Act: -0.0002

Data Index: 673278 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1079703 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0601. Min Act: -0.0002

Data Index: 281136 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0587. Min Act: -0.0002

Data Index: 118289 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0577. Min Act: -0.0001

Data Index: 403247 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0552. Min Act: -0.0002

Data Index: 17451 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0572. Min Act: -0.0002

Data Index: 198854 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0568. Min Act: -0.0002

Data Index: 131920 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1042111 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0553. Min Act: -0.0001

Data Index: 263429 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0556. Min Act: -0.0002

Data Index: 19065 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0546. Min Act: -0.0002

Data Index: 998391 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0544. Min Act: -0.0001

Data Index: 273780 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1165929 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0520. Min Act: -0.0002

Data Index: 336338 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1300572 (C4 (Web Text))

Max Activating Token Index: 448