Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1366 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.9840. Min Act: -0.0000

Data Index: 1630603 (Python Code)

Max Activating Token Index: 301

Text #1

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.7547. Min Act: -0.0000

Data Index: 1523397 (Python Code)

Max Activating Token Index: 1017

Text #2

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1622041 (Python Code)

Max Activating Token Index: 133

Text #3

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.7323. Min Act: -0.0000

Data Index: 1454277 (Python Code)

Max Activating Token Index: 406

Text #4

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6702. Min Act: -0.0000

Data Index: 1647482 (Python Code)

Max Activating Token Index: 108

Text #5

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6696. Min Act: -0.0000

Data Index: 1495219 (Python Code)

Max Activating Token Index: 944

Text #6

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6639. Min Act: -0.0000

Data Index: 1641839 (Python Code)

Max Activating Token Index: 737

Text #7

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1475164 (Python Code)

Max Activating Token Index: 998

Text #8

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6297. Min Act: -0.0000

Data Index: 1396292 (Python Code)

Max Activating Token Index: 228

Text #9

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6492. Min Act: -0.0000

Data Index: 1395269 (Python Code)

Max Activating Token Index: 329

Text #10

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1370500 (Python Code)

Max Activating Token Index: 902

Text #11

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.5888. Min Act: -0.0000

Data Index: 1447360 (Python Code)

Max Activating Token Index: 356

Text #12

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6034. Min Act: -0.0000

Data Index: 261911 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1590435 (Python Code)

Max Activating Token Index: 776

Text #14

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.5997. Min Act: -0.0000

Data Index: 1494623 (Python Code)

Max Activating Token Index: 191

Text #15

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.5990. Min Act: -0.0000

Data Index: 97170 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6128. Min Act: -0.0000

Data Index: 1389071 (Python Code)

Max Activating Token Index: 161

Text #17

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1611209 (Python Code)

Max Activating Token Index: 432

Text #18

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.5721. Min Act: -0.0000

Data Index: 1483077 (Python Code)

Max Activating Token Index: 491

Text #19

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6254. Min Act: -0.0000

Data Index: 1530280 (Python Code)

Max Activating Token Index: 875