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

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

Neuron 2268 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.7694. Min Act: -0.0000

Data Index: 1005737 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.4582. Min Act: -0.0000

Data Index: 1535808 (Python Code)

Max Activating Token Index: 114

Text #2

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1515993 (Python Code)

Max Activating Token Index: 105

Text #3

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.4498. Min Act: -0.0000

Data Index: 1526759 (Python Code)

Max Activating Token Index: 260

Text #4

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.4239. Min Act: -0.0000

Data Index: 1411625 (Python Code)

Max Activating Token Index: 126

Text #5

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.4519. Min Act: -0.0000

Data Index: 1469653 (Python Code)

Max Activating Token Index: 687

Text #6

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.4256. Min Act: -0.0000

Data Index: 1635647 (Python Code)

Max Activating Token Index: 125

Text #7

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1426415 (Python Code)

Max Activating Token Index: 250

Text #8

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.4011. Min Act: -0.0000

Data Index: 1518783 (Python Code)

Max Activating Token Index: 93

Text #9

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.4147. Min Act: -0.0000

Data Index: 1543179 (Python Code)

Max Activating Token Index: 156

Text #10

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.3944. Min Act: -0.0000

Data Index: 1440888 (Python Code)

Max Activating Token Index: 745

Text #11

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.3908. Min Act: -0.0000

Data Index: 1470485 (Python Code)

Max Activating Token Index: 611

Text #12

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1620576 (Python Code)

Max Activating Token Index: 139

Text #13

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.3696. Min Act: -0.0000

Data Index: 1428300 (Python Code)

Max Activating Token Index: 690

Text #14

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.3591. Min Act: -0.0000

Data Index: 1451166 (Python Code)

Max Activating Token Index: 41

Text #15

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.4011. Min Act: -0.0000

Data Index: 1534400 (Python Code)

Max Activating Token Index: 308

Text #16

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1389455 (Python Code)

Max Activating Token Index: 224

Text #17

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.3679. Min Act: -0.0000

Data Index: 1567044 (Python Code)

Max Activating Token Index: 191

Text #18

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.3641. Min Act: -0.0000

Data Index: 1432821 (Python Code)

Max Activating Token Index: 97

Text #19

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.3755. Min Act: -0.0000

Data Index: 1472384 (Python Code)

Max Activating Token Index: 208