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

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

Neuron 1567 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: 0.0895. Min Range: -0.0895

Max Act: 0.0878. Min Act: -0.0002

Data Index: 144229 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0895. Min Act: -0.0001

Data Index: 452988 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0789. Min Act: -0.0002

Data Index: 869959 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0765. Min Act: -0.0002

Data Index: 1307892 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0749. Min Act: -0.0001

Data Index: 801015 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0739. Min Act: -0.0001

Data Index: 572453 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0656. Min Act: -0.0002

Data Index: 309425 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0722. Min Act: -0.0001

Data Index: 279498 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0743. Min Act: -0.0001

Data Index: 980679 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0660. Min Act: -0.0001

Data Index: 1012312 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0681. Min Act: -0.0001

Data Index: 950273 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0685. Min Act: -0.0001

Data Index: 314596 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0633. Min Act: -0.0002

Data Index: 185080 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0670. Min Act: -0.0002

Data Index: 298013 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0649. Min Act: -0.0001

Data Index: 1187337 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0670. Min Act: -0.0002

Data Index: 1108996 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0619. Min Act: -0.0002

Data Index: 918892 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0659. Min Act: -0.0001

Data Index: 825336 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0658. Min Act: -0.0001

Data Index: 707777 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0644. Min Act: -0.0001

Data Index: 88307 (C4 (Web Text))

Max Activating Token Index: 499