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

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

Neuron 10 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.4083. Min Act: -0.0002

Data Index: 115535 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3763. Min Act: -0.0002

Data Index: 149286 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.4174. Min Act: -0.0002

Data Index: 639457 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.4246. Min Act: -0.0002

Data Index: 505311 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3697. Min Act: -0.0002

Data Index: 851733 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3602. Min Act: -0.0002

Data Index: 802854 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3807. Min Act: -0.0002

Data Index: 719583 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3914. Min Act: -0.0002

Data Index: 833724 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3141. Min Act: -0.0002

Data Index: 678745 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3830. Min Act: -0.0002

Data Index: 354272 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.4317. Min Act: -0.0002

Data Index: 1099528 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3647. Min Act: -0.0002

Data Index: 794222 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3468. Min Act: -0.0002

Data Index: 524210 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3615. Min Act: -0.0002

Data Index: 262992 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3650. Min Act: -0.0002

Data Index: 285086 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3490. Min Act: -0.0002

Data Index: 383329 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.2957. Min Act: -0.0002

Data Index: 524180 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3611. Min Act: -0.0002

Data Index: 640278 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3232. Min Act: -0.0002

Data Index: 1158757 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3501. Min Act: -0.0002

Data Index: 401462 (C4 (Web Text))

Max Activating Token Index: 473