Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 255 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.1031. Min Act: -0.0002

Data Index: 787737 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0967. Min Act: -0.0002

Data Index: 1329805 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0960. Min Act: -0.0002

Data Index: 471983 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0919. Min Act: -0.0002

Data Index: 373405 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0943. Min Act: -0.0002

Data Index: 46254 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0956. Min Act: -0.0002

Data Index: 781982 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0880. Min Act: -0.0002

Data Index: 502548 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1338567 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0928. Min Act: -0.0002

Data Index: 760332 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0899. Min Act: -0.0002

Data Index: 1170984 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0884. Min Act: -0.0002

Data Index: 420233 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0966. Min Act: -0.0002

Data Index: 188829 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0818. Min Act: -0.0002

Data Index: 572960 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0916. Min Act: -0.0002

Data Index: 39407 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0867. Min Act: -0.0002

Data Index: 725284 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0907. Min Act: -0.0002

Data Index: 1055515 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0857. Min Act: -0.0002

Data Index: 368575 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0838. Min Act: -0.0002

Data Index: 829151 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0880. Min Act: -0.0002

Data Index: 506762 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0813. Min Act: -0.0002

Data Index: 992765 (C4 (Web Text))

Max Activating Token Index: 836