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

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

Neuron 3098 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0898. Min Act: -0.0001

Data Index: 1417782 (Python Code)

Max Activating Token Index: 422

Text #1

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0886. Min Act: -0.0001

Data Index: 1579053 (Python Code)

Max Activating Token Index: 373

Text #2

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0790. Min Act: -0.0001

Data Index: 1496998 (Python Code)

Max Activating Token Index: 587

Text #3

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0823. Min Act: -0.0001

Data Index: 248195 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0764. Min Act: -0.0001

Data Index: 1436641 (Python Code)

Max Activating Token Index: 349

Text #5

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0642. Min Act: -0.0001

Data Index: 1422419 (Python Code)

Max Activating Token Index: 201

Text #6

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0732. Min Act: -0.0001

Data Index: 1387233 (Python Code)

Max Activating Token Index: 121

Text #7

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0685. Min Act: -0.0001

Data Index: 1576612 (Python Code)

Max Activating Token Index: 74

Text #8

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0691. Min Act: -0.0001

Data Index: 413730 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1407294 (Python Code)

Max Activating Token Index: 607

Text #10

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0567. Min Act: -0.0001

Data Index: 14072 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0528. Min Act: -0.0001

Data Index: 1427241 (Python Code)

Max Activating Token Index: 712

Text #12

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0711. Min Act: -0.0001

Data Index: 678605 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0668. Min Act: -0.0001

Data Index: 1476169 (Python Code)

Max Activating Token Index: 505

Text #14

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0660. Min Act: -0.0001

Data Index: 1317030 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0657. Min Act: -0.0001

Data Index: 222712 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0619. Min Act: -0.0001

Data Index: 1473280 (Python Code)

Max Activating Token Index: 249

Text #17

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0635. Min Act: -0.0001

Data Index: 842572 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1526761 (Python Code)

Max Activating Token Index: 340

Text #19

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0662. Min Act: -0.0001

Data Index: 1538753 (Python Code)

Max Activating Token Index: 88