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

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

Neuron 2518 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5591. Min Range: -2.5591

Max Act: 2.4575. Min Act: -0.0001

Data Index: 1621461 (Python Code)

Max Activating Token Index: 22

Text #1

Max Range: 2.5591. Min Range: -2.5591

Max Act: 2.5072. Min Act: -0.0000

Data Index: 1616078 (Python Code)

Max Activating Token Index: 58

Text #2

Max Range: 2.5591. Min Range: -2.5591

Max Act: 2.4140. Min Act: -0.0000

Data Index: 1556015 (Python Code)

Max Activating Token Index: 418

Text #3

Max Range: 2.5591. Min Range: -2.5591

Max Act: 2.5591. Min Act: -0.0000

Data Index: 1444315 (Python Code)

Max Activating Token Index: 200

Text #4

Max Range: 2.5591. Min Range: -2.5591

Max Act: 2.2873. Min Act: -0.0001

Data Index: 1451457 (Python Code)

Max Activating Token Index: 981

Text #5

Max Range: 2.5591. Min Range: -2.5591

Max Act: 2.1485. Min Act: -0.0000

Data Index: 1508918 (Python Code)

Max Activating Token Index: 179

Text #6

Max Range: 2.5591. Min Range: -2.5591

Max Act: 1.9538. Min Act: -0.0000

Data Index: 691968 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 2.5591. Min Range: -2.5591

Max Act: 1.9254. Min Act: -0.0000

Data Index: 1385257 (Python Code)

Max Activating Token Index: 995

Text #8

Max Range: 2.5591. Min Range: -2.5591

Max Act: 1.8510. Min Act: -0.0000

Data Index: 1483190 (Python Code)

Max Activating Token Index: 36

Text #9

Max Range: 2.5591. Min Range: -2.5591

Max Act: 1.7667. Min Act: -0.0000

Data Index: 1372167 (Python Code)

Max Activating Token Index: 20

Text #10

Max Range: 2.5591. Min Range: -2.5591

Max Act: 1.7823. Min Act: -0.0000

Data Index: 1447913 (Python Code)

Max Activating Token Index: 44

Text #11

Max Range: 2.5591. Min Range: -2.5591

Max Act: 1.6774. Min Act: -0.0000

Data Index: 1562580 (Python Code)

Max Activating Token Index: 108

Text #12

Max Range: 2.5591. Min Range: -2.5591

Max Act: 1.6735. Min Act: -0.0001

Data Index: 1404115 (Python Code)

Max Activating Token Index: 161

Text #13

Max Range: 2.5591. Min Range: -2.5591

Max Act: 1.7321. Min Act: -0.0000

Data Index: 1533914 (Python Code)

Max Activating Token Index: 325

Text #14

Max Range: 2.5591. Min Range: -2.5591

Max Act: 1.6449. Min Act: -0.0000

Data Index: 1580228 (Python Code)

Max Activating Token Index: 734

Text #15

Max Range: 2.5591. Min Range: -2.5591

Max Act: 1.7141. Min Act: -0.0000

Data Index: 984946 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 2.5591. Min Range: -2.5591

Max Act: 1.6246. Min Act: -0.0000

Data Index: 1459165 (Python Code)

Max Activating Token Index: 508

Text #17

Max Range: 2.5591. Min Range: -2.5591

Max Act: 1.6101. Min Act: -0.0000

Data Index: 1228488 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 2.5591. Min Range: -2.5591

Max Act: 1.6049. Min Act: -0.0000

Data Index: 1395882 (Python Code)

Max Activating Token Index: 140

Text #19

Max Range: 2.5591. Min Range: -2.5591

Max Act: 1.3479. Min Act: -0.0000

Data Index: 1441776 (Python Code)

Max Activating Token Index: 343