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

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

Neuron 2431 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: 0.0961. Min Range: -0.0961

Max Act: 0.0961. Min Act: -0.0002

Data Index: 1527865 (Python Code)

Max Activating Token Index: 910

Text #1

Max Range: 0.0961. Min Range: -0.0961

Max Act: 0.0927. Min Act: -0.0002

Data Index: 340694 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 0.0961. Min Range: -0.0961

Max Act: 0.0893. Min Act: -0.0002

Data Index: 282630 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.0961. Min Range: -0.0961

Max Act: 0.0934. Min Act: -0.0002

Data Index: 418096 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.0961. Min Range: -0.0961

Max Act: 0.0735. Min Act: -0.0002

Data Index: 212845 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 0.0961. Min Range: -0.0961

Max Act: 0.0799. Min Act: -0.0002

Data Index: 1648481 (Python Code)

Max Activating Token Index: 778

Text #6

Max Range: 0.0961. Min Range: -0.0961

Max Act: 0.0824. Min Act: -0.0002

Data Index: 1439341 (Python Code)

Max Activating Token Index: 256

Text #7

Max Range: 0.0961. Min Range: -0.0961

Max Act: 0.0801. Min Act: -0.0002

Data Index: 1458554 (Python Code)

Max Activating Token Index: 683

Text #8

Max Range: 0.0961. Min Range: -0.0961

Max Act: 0.0804. Min Act: -0.0002

Data Index: 1490714 (Python Code)

Max Activating Token Index: 222

Text #9

Max Range: 0.0961. Min Range: -0.0961

Max Act: 0.0760. Min Act: -0.0002

Data Index: 503164 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.0961. Min Range: -0.0961

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1475568 (Python Code)

Max Activating Token Index: 739

Text #11

Max Range: 0.0961. Min Range: -0.0961

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1592398 (Python Code)

Max Activating Token Index: 894

Text #12

Max Range: 0.0961. Min Range: -0.0961

Max Act: 0.0765. Min Act: -0.0002

Data Index: 1579042 (Python Code)

Max Activating Token Index: 250

Text #13

Max Range: 0.0961. Min Range: -0.0961

Max Act: 0.0752. Min Act: -0.0002

Data Index: 130242 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.0961. Min Range: -0.0961

Max Act: 0.0651. Min Act: -0.0002

Data Index: 766105 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.0961. Min Range: -0.0961

Max Act: 0.0745. Min Act: -0.0002

Data Index: 1500801 (Python Code)

Max Activating Token Index: 204

Text #16

Max Range: 0.0961. Min Range: -0.0961

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1143071 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.0961. Min Range: -0.0961

Max Act: 0.0736. Min Act: -0.0002

Data Index: 1653038 (Python Code)

Max Activating Token Index: 632

Text #18

Max Range: 0.0961. Min Range: -0.0961

Max Act: 0.0706. Min Act: -0.0002

Data Index: 772176 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 0.0961. Min Range: -0.0961

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1031435 (C4 (Web Text))

Max Activating Token Index: 611