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

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

Neuron 1402 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: 0.0772. Min Range: -0.0772

Max Act: 0.0772. Min Act: -0.0002

Data Index: 212843 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0718. Min Act: -0.0002

Data Index: 629019 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0704. Min Act: -0.0002

Data Index: 606451 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1306699 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0661. Min Act: -0.0002

Data Index: 152443 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0694. Min Act: -0.0002

Data Index: 539445 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1037644 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0666. Min Act: -0.0002

Data Index: 175094 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0673. Min Act: -0.0002

Data Index: 187822 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1191383 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0653. Min Act: -0.0002

Data Index: 61821 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1059026 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0659. Min Act: -0.0002

Data Index: 311514 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0659. Min Act: -0.0002

Data Index: 230128 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0652. Min Act: -0.0002

Data Index: 175864 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0649. Min Act: -0.0002

Data Index: 420584 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0607. Min Act: -0.0002

Data Index: 619868 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1255176 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0636. Min Act: -0.0002

Data Index: 643513 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0657. Min Act: -0.0002

Data Index: 189190 (C4 (Web Text))

Max Activating Token Index: 934