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

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

Neuron 5 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0681. Min Act: -0.0005

Data Index: 512567 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0637. Min Act: -0.0005

Data Index: 1215965 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0668. Min Act: -0.0005

Data Index: 776587 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0631. Min Act: -0.0005

Data Index: 723670 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0578. Min Act: -0.0005

Data Index: 1377880 (Python Code)

Max Activating Token Index: 860

Text #5

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0592. Min Act: -0.0005

Data Index: 1334311 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0572. Min Act: -0.0005

Data Index: 564542 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0655. Min Act: -0.0005

Data Index: 1099047 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0593. Min Act: -0.0005

Data Index: 762428 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0596. Min Act: -0.0005

Data Index: 1230358 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0589. Min Act: -0.0005

Data Index: 316372 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0588. Min Act: -0.0005

Data Index: 415435 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0528. Min Act: -0.0005

Data Index: 283446 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0548. Min Act: -0.0005

Data Index: 480205 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0589. Min Act: -0.0005

Data Index: 1352399 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0639. Min Act: -0.0005

Data Index: 750662 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0556. Min Act: -0.0005

Data Index: 375701 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0578. Min Act: -0.0005

Data Index: 742460 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0574. Min Act: -0.0005

Data Index: 1553526 (Python Code)

Max Activating Token Index: 468

Text #19

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0553. Min Act: -0.0005

Data Index: 1391567 (Python Code)

Max Activating Token Index: 637