Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1656 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1475. Min Act: -0.0002

Data Index: 1512855 (Python Code)

Max Activating Token Index: 11

Text #1

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1273. Min Act: -0.0002

Data Index: 955683 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1290. Min Act: -0.0002

Data Index: 1384433 (Python Code)

Max Activating Token Index: 10

Text #3

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1172. Min Act: -0.0002

Data Index: 339408 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1047. Min Act: -0.0002

Data Index: 79545 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1109. Min Act: -0.0002

Data Index: 97719 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1098. Min Act: -0.0001

Data Index: 1314549 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0983. Min Act: -0.0002

Data Index: 397464 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1026. Min Act: -0.0002

Data Index: 346464 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1002. Min Act: -0.0002

Data Index: 872266 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1048. Min Act: -0.0002

Data Index: 491087 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1018. Min Act: -0.0002

Data Index: 1074166 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1035. Min Act: -0.0002

Data Index: 191001 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0954. Min Act: -0.0002

Data Index: 215712 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1003. Min Act: -0.0002

Data Index: 262109 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1000. Min Act: -0.0001

Data Index: 1019334 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1015. Min Act: -0.0001

Data Index: 362696 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1025. Min Act: -0.0001

Data Index: 599803 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1042. Min Act: -0.0002

Data Index: 1227528 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0969. Min Act: -0.0001

Data Index: 769489 (C4 (Web Text))

Max Activating Token Index: 350