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

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

Neuron 2365 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: 0.0781. Min Range: -0.0781

Max Act: 0.0781. Min Act: -0.0002

Data Index: 349049 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0685. Min Act: -0.0002

Data Index: 461404 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1304442 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0654. Min Act: -0.0001

Data Index: 375692 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0634. Min Act: -0.0001

Data Index: 762751 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1181384 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0552. Min Act: -0.0002

Data Index: 503371 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0633. Min Act: -0.0002

Data Index: 286094 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0580. Min Act: -0.0001

Data Index: 907526 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0577. Min Act: -0.0001

Data Index: 833936 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0617. Min Act: -0.0001

Data Index: 571045 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0631. Min Act: -0.0001

Data Index: 1610608 (Python Code)

Max Activating Token Index: 27

Text #12

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0618. Min Act: -0.0001

Data Index: 947827 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1236858 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0653. Min Act: -0.0002

Data Index: 302359 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0624. Min Act: -0.0002

Data Index: 1297684 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0618. Min Act: -0.0002

Data Index: 398601 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0566. Min Act: -0.0001

Data Index: 1146875 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0587. Min Act: -0.0002

Data Index: 273989 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0595. Min Act: -0.0001

Data Index: 533781 (C4 (Web Text))

Max Activating Token Index: 522