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

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

Neuron 2821 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1005. Min Range: -0.1005

Max Act: 0.1005. Min Act: -0.0000

Data Index: 798347 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.1005. Min Range: -0.1005

Max Act: 0.0824. Min Act: -0.0000

Data Index: 1003455 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 0.1005. Min Range: -0.1005

Max Act: 0.0697. Min Act: -0.0001

Data Index: 573690 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 0.1005. Min Range: -0.1005

Max Act: 0.0668. Min Act: -0.0000

Data Index: 229593 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.1005. Min Range: -0.1005

Max Act: 0.0608. Min Act: -0.0000

Data Index: 1572827 (Python Code)

Max Activating Token Index: 823

Text #5

Max Range: 0.1005. Min Range: -0.1005

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1525556 (Python Code)

Max Activating Token Index: 823

Text #6

Max Range: 0.1005. Min Range: -0.1005

Max Act: 0.0592. Min Act: -0.0001

Data Index: 1438862 (Python Code)

Max Activating Token Index: 744

Text #7

Max Range: 0.1005. Min Range: -0.1005

Max Act: 0.0612. Min Act: -0.0001

Data Index: 1344399 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 0.1005. Min Range: -0.1005

Max Act: 0.0605. Min Act: -0.0000

Data Index: 379546 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 0.1005. Min Range: -0.1005

Max Act: 0.0605. Min Act: -0.0001

Data Index: 870509 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.1005. Min Range: -0.1005

Max Act: 0.0615. Min Act: -0.0001

Data Index: 966422 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 0.1005. Min Range: -0.1005

Max Act: 0.0614. Min Act: -0.0000

Data Index: 1581003 (Python Code)

Max Activating Token Index: 237

Text #12

Max Range: 0.1005. Min Range: -0.1005

Max Act: 0.0537. Min Act: -0.0000

Data Index: 1397600 (Python Code)

Max Activating Token Index: 157

Text #13

Max Range: 0.1005. Min Range: -0.1005

Max Act: 0.0590. Min Act: -0.0000

Data Index: 1272061 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.1005. Min Range: -0.1005

Max Act: 0.0594. Min Act: -0.0000

Data Index: 1638950 (Python Code)

Max Activating Token Index: 760

Text #15

Max Range: 0.1005. Min Range: -0.1005

Max Act: 0.0580. Min Act: -0.0000

Data Index: 1509827 (Python Code)

Max Activating Token Index: 152

Text #16

Max Range: 0.1005. Min Range: -0.1005

Max Act: 0.0583. Min Act: -0.0000

Data Index: 1586071 (Python Code)

Max Activating Token Index: 888

Text #17

Max Range: 0.1005. Min Range: -0.1005

Max Act: 0.0586. Min Act: -0.0000

Data Index: 800671 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.1005. Min Range: -0.1005

Max Act: 0.0592. Min Act: -0.0000

Data Index: 590519 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.1005. Min Range: -0.1005

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1382012 (Python Code)

Max Activating Token Index: 227