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

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

Neuron 513 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: 0.0756. Min Range: -0.0756

Max Act: 0.0755. Min Act: -0.0005

Data Index: 1120376 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0756. Min Act: -0.0005

Data Index: 1302794 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0742. Min Act: -0.0005

Data Index: 1072441 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0702. Min Act: -0.0005

Data Index: 888319 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0544. Min Act: -0.0005

Data Index: 84537 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0704. Min Act: -0.0005

Data Index: 465339 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0667. Min Act: -0.0005

Data Index: 204939 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0644. Min Act: -0.0005

Data Index: 798439 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0634. Min Act: -0.0005

Data Index: 735482 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0625. Min Act: -0.0005

Data Index: 1272615 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0642. Min Act: -0.0005

Data Index: 17843 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0650. Min Act: -0.0005

Data Index: 956265 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0639. Min Act: -0.0005

Data Index: 74302 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0598. Min Act: -0.0005

Data Index: 158883 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0584. Min Act: -0.0005

Data Index: 1287375 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0600. Min Act: -0.0005

Data Index: 527409 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0625. Min Act: -0.0005

Data Index: 1069805 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0580. Min Act: -0.0005

Data Index: 879108 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0633. Min Act: -0.0005

Data Index: 719983 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0522. Min Act: -0.0005

Data Index: 1221693 (C4 (Web Text))

Max Activating Token Index: 455