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

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

Neuron 1747 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0782. Min Act: -0.0006

Data Index: 262768 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0704. Min Act: -0.0006

Data Index: 987595 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0675. Min Act: -0.0006

Data Index: 1028872 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0652. Min Act: -0.0006

Data Index: 444826 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0636. Min Act: -0.0006

Data Index: 834205 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0610. Min Act: -0.0006

Data Index: 365050 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0617. Min Act: -0.0006

Data Index: 1248240 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0608. Min Act: -0.0006

Data Index: 91680 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0609. Min Act: -0.0006

Data Index: 308502 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0607. Min Act: -0.0006

Data Index: 489025 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0596. Min Act: -0.0006

Data Index: 1169121 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0589. Min Act: -0.0006

Data Index: 331241 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0584. Min Act: -0.0006

Data Index: 1117962 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0559. Min Act: -0.0005

Data Index: 1351052 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0587. Min Act: -0.0006

Data Index: 1060658 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0561. Min Act: -0.0006

Data Index: 805481 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0561. Min Act: -0.0006

Data Index: 213630 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0550. Min Act: -0.0006

Data Index: 881345 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0570. Min Act: -0.0006

Data Index: 471042 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0568. Min Act: -0.0005

Data Index: 1255909 (C4 (Web Text))

Max Activating Token Index: 113