Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3559 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0884. Min Act: -0.0002

Data Index: 1168698 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0906. Min Act: -0.0002

Data Index: 1250567 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0798. Min Act: -0.0002

Data Index: 1242044 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0802. Min Act: -0.0002

Data Index: 234231 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1359766 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0784. Min Act: -0.0002

Data Index: 1062093 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0774. Min Act: -0.0002

Data Index: 1292900 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0753. Min Act: -0.0002

Data Index: 464378 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0744. Min Act: -0.0002

Data Index: 1140805 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0736. Min Act: -0.0002

Data Index: 818909 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0734. Min Act: -0.0002

Data Index: 1164614 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0682. Min Act: -0.0002

Data Index: 390030 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0713. Min Act: -0.0002

Data Index: 1113196 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0679. Min Act: -0.0002

Data Index: 255842 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0675. Min Act: -0.0002

Data Index: 532128 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1182537 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0692. Min Act: -0.0002

Data Index: 431965 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1358204 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0660. Min Act: -0.0002

Data Index: 243546 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1064086 (C4 (Web Text))

Max Activating Token Index: 570