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

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

Neuron 1937 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.8868. Min Act: 0.0002

Data Index: 1374085 (Python Code)

Max Activating Token Index: 157

Text #1

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.9339. Min Act: 0.0001

Data Index: 1405528 (Python Code)

Max Activating Token Index: 314

Text #2

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.8892. Min Act: 0.0001

Data Index: 1560733 (Python Code)

Max Activating Token Index: 385

Text #3

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7938. Min Act: -0.0000

Data Index: 1547481 (Python Code)

Max Activating Token Index: 550

Text #4

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7703. Min Act: 0.0000

Data Index: 1568575 (Python Code)

Max Activating Token Index: 107

Text #5

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7491. Min Act: 0.0000

Data Index: 1360701 (Python Code)

Max Activating Token Index: 152

Text #6

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7569. Min Act: 0.0001

Data Index: 1441558 (Python Code)

Max Activating Token Index: 87

Text #7

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7368. Min Act: 0.0000

Data Index: 1656918 (Python Code)

Max Activating Token Index: 81

Text #8

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7066. Min Act: 0.0000

Data Index: 1485256 (Python Code)

Max Activating Token Index: 237

Text #9

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7118. Min Act: -0.0000

Data Index: 1480623 (Python Code)

Max Activating Token Index: 93

Text #10

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6864. Min Act: -0.0000

Data Index: 1656943 (Python Code)

Max Activating Token Index: 468

Text #11

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7022. Min Act: 0.0001

Data Index: 1644053 (Python Code)

Max Activating Token Index: 1022

Text #12

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6525. Min Act: 0.0000

Data Index: 1653983 (Python Code)

Max Activating Token Index: 272

Text #13

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6705. Min Act: -0.0000

Data Index: 1398829 (Python Code)

Max Activating Token Index: 1011

Text #14

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6354. Min Act: 0.0000

Data Index: 1455919 (Python Code)

Max Activating Token Index: 230

Text #15

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6356. Min Act: 0.0000

Data Index: 1642128 (Python Code)

Max Activating Token Index: 533

Text #16

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6327. Min Act: -0.0000

Data Index: 1504535 (Python Code)

Max Activating Token Index: 482

Text #17

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6522. Min Act: 0.0002

Data Index: 1507940 (Python Code)

Max Activating Token Index: 313

Text #18

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6049. Min Act: 0.0001

Data Index: 1470720 (Python Code)

Max Activating Token Index: 840

Text #19

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6410. Min Act: -0.0000

Data Index: 1557270 (Python Code)

Max Activating Token Index: 159