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

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

Neuron 2844 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: 0.1297. Min Range: -0.1297

Max Act: 0.1297. Min Act: -0.0002

Data Index: 176939 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1090. Min Act: -0.0001

Data Index: 1080416 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1024. Min Act: -0.0002

Data Index: 739921 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0994. Min Act: -0.0002

Data Index: 1090976 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0890. Min Act: -0.0001

Data Index: 354265 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0967. Min Act: -0.0002

Data Index: 139084 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0950. Min Act: -0.0001

Data Index: 875904 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0916. Min Act: -0.0002

Data Index: 914270 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0870. Min Act: -0.0001

Data Index: 129424 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0820. Min Act: -0.0001

Data Index: 969209 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1053915 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0821. Min Act: -0.0001

Data Index: 182985 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0781. Min Act: -0.0001

Data Index: 1098371 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1187161 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0792. Min Act: -0.0001

Data Index: 782687 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0792. Min Act: -0.0001

Data Index: 231604 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0731. Min Act: -0.0001

Data Index: 247242 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1302002 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0753. Min Act: -0.0002

Data Index: 939557 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0812. Min Act: -0.0002

Data Index: 20887 (C4 (Web Text))

Max Activating Token Index: 532