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

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

Neuron 4371 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1520421 (Python Code)

Max Activating Token Index: 300

Text #1

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1581860 (Python Code)

Max Activating Token Index: 997

Text #2

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1479776 (Python Code)

Max Activating Token Index: 257

Text #3

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1381614 (Python Code)

Max Activating Token Index: 691

Text #4

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1409511 (Python Code)

Max Activating Token Index: 988

Text #5

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1530713 (Python Code)

Max Activating Token Index: 325

Text #6

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1431489 (Python Code)

Max Activating Token Index: 1001

Text #7

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1533740 (Python Code)

Max Activating Token Index: 18

Text #8

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0086. Min Act: -0.0002

Data Index: 1647200 (Python Code)

Max Activating Token Index: 988

Text #9

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1601814 (Python Code)

Max Activating Token Index: 977

Text #10

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1580267 (Python Code)

Max Activating Token Index: 969

Text #11

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1460000 (Python Code)

Max Activating Token Index: 1018

Text #12

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1646588 (Python Code)

Max Activating Token Index: 1001

Text #13

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1606722 (Python Code)

Max Activating Token Index: 23

Text #14

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1528322 (Python Code)

Max Activating Token Index: 856

Text #15

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1495178 (Python Code)

Max Activating Token Index: 241

Text #16

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1618194 (Python Code)

Max Activating Token Index: 1005

Text #17

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1611120 (Python Code)

Max Activating Token Index: 915

Text #18

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1440613 (Python Code)

Max Activating Token Index: 215

Text #19

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1442882 (Python Code)

Max Activating Token Index: 131