Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4771 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.3096. Min Act: -0.0001

Data Index: 231553 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2428. Min Act: -0.0001

Data Index: 1277401 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2409. Min Act: -0.0001

Data Index: 680741 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2377. Min Act: -0.0001

Data Index: 646683 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2172. Min Act: -0.0001

Data Index: 689224 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2363. Min Act: -0.0001

Data Index: 777243 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.1890. Min Act: -0.0001

Data Index: 914524 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2201. Min Act: -0.0001

Data Index: 116733 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.1870. Min Act: -0.0001

Data Index: 304266 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2026. Min Act: -0.0001

Data Index: 1149010 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2091. Min Act: -0.0001

Data Index: 585404 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2156. Min Act: -0.0001

Data Index: 1077997 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.1953. Min Act: -0.0001

Data Index: 456785 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2155. Min Act: -0.0001

Data Index: 587573 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.1867. Min Act: -0.0001

Data Index: 415291 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.1909. Min Act: -0.0001

Data Index: 1353589 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.1882. Min Act: -0.0001

Data Index: 618099 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2324. Min Act: -0.0001

Data Index: 86902 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2255. Min Act: -0.0001

Data Index: 286729 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2088. Min Act: -0.0001

Data Index: 463395 (C4 (Web Text))

Max Activating Token Index: 970