Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3179 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0838. Min Act: -0.0001

Data Index: 800400 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0777. Min Act: -0.0001

Data Index: 657551 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0722. Min Act: -0.0001

Data Index: 170904 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0721. Min Act: -0.0001

Data Index: 983669 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0706. Min Act: -0.0001

Data Index: 120660 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0696. Min Act: -0.0001

Data Index: 681799 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0684. Min Act: -0.0002

Data Index: 393538 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0674. Min Act: -0.0001

Data Index: 1160868 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0684. Min Act: -0.0001

Data Index: 432389 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0675. Min Act: -0.0001

Data Index: 294885 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0671. Min Act: -0.0001

Data Index: 39877 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0672. Min Act: -0.0001

Data Index: 1038314 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0684. Min Act: -0.0001

Data Index: 380450 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0663. Min Act: -0.0001

Data Index: 798026 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0659. Min Act: -0.0001

Data Index: 176976 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0664. Min Act: -0.0001

Data Index: 94891 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0671. Min Act: -0.0001

Data Index: 1162873 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1153651 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0654. Min Act: -0.0001

Data Index: 60101 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0658. Min Act: -0.0001

Data Index: 613391 (C4 (Web Text))

Max Activating Token Index: 558