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

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

Neuron 63 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: 0.0804. Min Range: -0.0804

Max Act: 0.0804. Min Act: -0.0002

Data Index: 237592 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0686. Min Act: -0.0001

Data Index: 443863 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0679. Min Act: -0.0001

Data Index: 945660 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0690. Min Act: -0.0001

Data Index: 148541 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0678. Min Act: -0.0002

Data Index: 777333 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0656. Min Act: -0.0001

Data Index: 130366 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0659. Min Act: -0.0002

Data Index: 691460 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0656. Min Act: -0.0000

Data Index: 540698 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0640. Min Act: -0.0001

Data Index: 1059926 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0622. Min Act: -0.0002

Data Index: 725677 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0614. Min Act: -0.0002

Data Index: 125890 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0606. Min Act: -0.0001

Data Index: 242439 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0615. Min Act: -0.0001

Data Index: 1101549 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0602. Min Act: -0.0001

Data Index: 83310 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1332536 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0570. Min Act: -0.0001

Data Index: 877930 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0612. Min Act: -0.0002

Data Index: 499635 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0599. Min Act: -0.0002

Data Index: 5210 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0593. Min Act: -0.0001

Data Index: 1087294 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0577. Min Act: -0.0001

Data Index: 453442 (C4 (Web Text))

Max Activating Token Index: 510