Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 422 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.1059. Min Act: -0.0002

Data Index: 18007 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0792. Min Act: -0.0002

Data Index: 647822 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0772. Min Act: -0.0002

Data Index: 6066 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0679. Min Act: -0.0002

Data Index: 375172 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0623. Min Act: -0.0001

Data Index: 51544 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0718. Min Act: -0.0002

Data Index: 1263522 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1148222 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0646. Min Act: -0.0001

Data Index: 899985 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0645. Min Act: -0.0001

Data Index: 357581 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0629. Min Act: -0.0002

Data Index: 940367 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0636. Min Act: -0.0002

Data Index: 718576 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0579. Min Act: -0.0002

Data Index: 685840 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0630. Min Act: -0.0001

Data Index: 1081501 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0550. Min Act: -0.0001

Data Index: 24171 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0570. Min Act: -0.0002

Data Index: 712853 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1270256 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0596. Min Act: -0.0001

Data Index: 863802 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0536. Min Act: -0.0001

Data Index: 233302 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0579. Min Act: -0.0002

Data Index: 607690 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0562. Min Act: -0.0001

Data Index: 464907 (C4 (Web Text))

Max Activating Token Index: 818