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

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

Neuron 3497 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: 0.4478. Min Range: -0.4478

Max Act: 0.4478. Min Act: -0.0001

Data Index: 1422523 (Python Code)

Max Activating Token Index: 840

Text #1

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3943. Min Act: -0.0001

Data Index: 1272515 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.4067. Min Act: -0.0001

Data Index: 760900 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3920. Min Act: -0.0001

Data Index: 487168 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3816. Min Act: -0.0001

Data Index: 1526455 (Python Code)

Max Activating Token Index: 985

Text #5

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3132. Min Act: -0.0001

Data Index: 838291 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3508. Min Act: -0.0001

Data Index: 230010 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3671. Min Act: -0.0001

Data Index: 779357 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3424. Min Act: -0.0001

Data Index: 1468127 (Python Code)

Max Activating Token Index: 680

Text #9

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3306. Min Act: -0.0001

Data Index: 686863 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3225. Min Act: -0.0001

Data Index: 1276434 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3187. Min Act: -0.0001

Data Index: 860052 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3106. Min Act: -0.0001

Data Index: 827846 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3075. Min Act: -0.0001

Data Index: 360827 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3053. Min Act: -0.0001

Data Index: 1356693 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3249. Min Act: -0.0001

Data Index: 1115769 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3205. Min Act: -0.0001

Data Index: 1216596 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.2926. Min Act: -0.0001

Data Index: 984920 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3115. Min Act: -0.0001

Data Index: 363430 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3211. Min Act: -0.0001

Data Index: 111423 (C4 (Web Text))

Max Activating Token Index: 175