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

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

Neuron 1051 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: 0.2081. Min Range: -0.2081

Max Act: 0.2030. Min Act: -0.0001

Data Index: 611835 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.2081. Min Act: -0.0001

Data Index: 642713 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1757. Min Act: -0.0001

Data Index: 1648277 (Python Code)

Max Activating Token Index: 850

Text #3

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1728. Min Act: -0.0001

Data Index: 643073 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1771. Min Act: -0.0001

Data Index: 1293675 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1808. Min Act: -0.0001

Data Index: 697314 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1821. Min Act: -0.0001

Data Index: 1289915 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1782. Min Act: -0.0001

Data Index: 1014493 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1670. Min Act: -0.0001

Data Index: 16098 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1636. Min Act: -0.0001

Data Index: 789447 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1581. Min Act: -0.0001

Data Index: 329728 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1569. Min Act: -0.0001

Data Index: 202514 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1788. Min Act: -0.0001

Data Index: 963854 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1672. Min Act: -0.0001

Data Index: 598308 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1534. Min Act: -0.0001

Data Index: 733314 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1618. Min Act: -0.0001

Data Index: 1038604 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1615. Min Act: -0.0001

Data Index: 930424 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1505. Min Act: -0.0001

Data Index: 302187 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1483. Min Act: -0.0001

Data Index: 1041236 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1623. Min Act: -0.0001

Data Index: 645727 (C4 (Web Text))

Max Activating Token Index: 279