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

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

Neuron 1531 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0749. Min Act: -0.0002

Data Index: 1641000 (Python Code)

Max Activating Token Index: 33

Text #1

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1069578 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1407246 (Python Code)

Max Activating Token Index: 599

Text #3

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1013268 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0587. Min Act: -0.0002

Data Index: 928077 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1037023 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0542. Min Act: -0.0002

Data Index: 1620332 (Python Code)

Max Activating Token Index: 36

Text #7

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0526. Min Act: -0.0002

Data Index: 984525 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1516174 (Python Code)

Max Activating Token Index: 620

Text #9

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1527691 (Python Code)

Max Activating Token Index: 525

Text #10

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1643433 (Python Code)

Max Activating Token Index: 274

Text #11

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0528. Min Act: -0.0002

Data Index: 473030 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1233106 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0524. Min Act: -0.0002

Data Index: 542706 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0500. Min Act: -0.0002

Data Index: 425612 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0499. Min Act: -0.0002

Data Index: 269266 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1285574 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1402973 (Python Code)

Max Activating Token Index: 755

Text #18

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1030720 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0504. Min Act: -0.0002

Data Index: 136521 (C4 (Web Text))

Max Activating Token Index: 200