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

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

Neuron 1788 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: 0.4985. Min Range: -0.4985

Max Act: 0.4985. Min Act: -0.0002

Data Index: 1651411 (Python Code)

Max Activating Token Index: 265

Text #1

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.4880. Min Act: -0.0002

Data Index: 1542799 (Python Code)

Max Activating Token Index: 252

Text #2

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.4601. Min Act: -0.0002

Data Index: 1412973 (Python Code)

Max Activating Token Index: 90

Text #3

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.4357. Min Act: -0.0002

Data Index: 1369814 (Python Code)

Max Activating Token Index: 177

Text #4

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.4254. Min Act: -0.0002

Data Index: 1512130 (Python Code)

Max Activating Token Index: 246

Text #5

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.4053. Min Act: -0.0001

Data Index: 1611658 (Python Code)

Max Activating Token Index: 108

Text #6

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3954. Min Act: -0.0002

Data Index: 1509584 (Python Code)

Max Activating Token Index: 299

Text #7

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.4048. Min Act: -0.0002

Data Index: 1629768 (Python Code)

Max Activating Token Index: 76

Text #8

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.4130. Min Act: -0.0002

Data Index: 1418824 (Python Code)

Max Activating Token Index: 233

Text #9

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.4029. Min Act: -0.0002

Data Index: 1626421 (Python Code)

Max Activating Token Index: 197

Text #10

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3926. Min Act: -0.0002

Data Index: 1362040 (Python Code)

Max Activating Token Index: 231

Text #11

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3862. Min Act: -0.0002

Data Index: 1621030 (Python Code)

Max Activating Token Index: 172

Text #12

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3750. Min Act: -0.0001

Data Index: 1499860 (Python Code)

Max Activating Token Index: 259

Text #13

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3653. Min Act: -0.0002

Data Index: 1515009 (Python Code)

Max Activating Token Index: 149

Text #14

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3700. Min Act: -0.0002

Data Index: 1427069 (Python Code)

Max Activating Token Index: 287

Text #15

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3735. Min Act: -0.0002

Data Index: 1565580 (Python Code)

Max Activating Token Index: 266

Text #16

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3626. Min Act: -0.0002

Data Index: 1540643 (Python Code)

Max Activating Token Index: 178

Text #17

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3870. Min Act: -0.0002

Data Index: 1550293 (Python Code)

Max Activating Token Index: 303

Text #18

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3628. Min Act: -0.0002

Data Index: 1378464 (Python Code)

Max Activating Token Index: 509

Text #19

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3565. Min Act: -0.0002

Data Index: 1555537 (Python Code)

Max Activating Token Index: 132