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

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

Neuron 3512 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2266. Min Range: -1.2266

Max Act: 1.1925. Min Act: -0.0000

Data Index: 1094541 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 1.2266. Min Range: -1.2266

Max Act: 1.0502. Min Act: -0.0000

Data Index: 1166865 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 1.2266. Min Range: -1.2266

Max Act: 1.2266. Min Act: -0.0000

Data Index: 712294 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 1.2266. Min Range: -1.2266

Max Act: 1.1107. Min Act: -0.0000

Data Index: 119804 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 1.2266. Min Range: -1.2266

Max Act: 1.0901. Min Act: -0.0000

Data Index: 733640 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 1.2266. Min Range: -1.2266

Max Act: 1.1370. Min Act: -0.0000

Data Index: 1300944 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.9263. Min Act: -0.0000

Data Index: 635122 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 1.2266. Min Range: -1.2266

Max Act: 1.0587. Min Act: -0.0000

Data Index: 687327 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.7800. Min Act: -0.0000

Data Index: 136752 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.8695. Min Act: -0.0000

Data Index: 1191785 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.8886. Min Act: -0.0000

Data Index: 855257 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.8395. Min Act: -0.0001

Data Index: 1038732 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.6715. Min Act: -0.0000

Data Index: 975185 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.8247. Min Act: -0.0000

Data Index: 470746 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.7970. Min Act: -0.0000

Data Index: 459578 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.8155. Min Act: -0.0000

Data Index: 319598 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.8631. Min Act: -0.0000

Data Index: 241473 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.8087. Min Act: -0.0000

Data Index: 252485 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.7556. Min Act: -0.0000

Data Index: 1252151 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.7749. Min Act: -0.0000

Data Index: 1190551 (C4 (Web Text))

Max Activating Token Index: 46