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

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

Neuron 2321 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: 0.9498. Min Range: -0.9498

Max Act: 0.9498. Min Act: -0.0002

Data Index: 340649 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.9365. Min Act: -0.0002

Data Index: 449927 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.8401. Min Act: -0.0002

Data Index: 1056755 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.8494. Min Act: -0.0002

Data Index: 506008 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7940. Min Act: -0.0002

Data Index: 548610 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7977. Min Act: -0.0001

Data Index: 307011 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7604. Min Act: -0.0002

Data Index: 144989 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7837. Min Act: -0.0001

Data Index: 869901 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7732. Min Act: -0.0002

Data Index: 43512 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.8088. Min Act: -0.0001

Data Index: 568607 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7550. Min Act: -0.0002

Data Index: 632079 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7686. Min Act: -0.0001

Data Index: 1170030 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7345. Min Act: -0.0001

Data Index: 1048225 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7551. Min Act: -0.0002

Data Index: 295208 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7371. Min Act: -0.0002

Data Index: 639950 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7801. Min Act: -0.0001

Data Index: 233430 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7503. Min Act: -0.0002

Data Index: 85085 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7317. Min Act: -0.0002

Data Index: 612433 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7030. Min Act: -0.0001

Data Index: 495223 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7723. Min Act: -0.0002

Data Index: 654247 (C4 (Web Text))

Max Activating Token Index: 991