Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4962 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7361. Min Range: -2.7361

Max Act: 2.7361. Min Act: -0.0000

Data Index: 1077674 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 2.7361. Min Range: -2.7361

Max Act: 2.3843. Min Act: -0.0000

Data Index: 716415 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 2.7361. Min Range: -2.7361

Max Act: 2.3730. Min Act: -0.0000

Data Index: 998819 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 2.7361. Min Range: -2.7361

Max Act: 2.2736. Min Act: -0.0000

Data Index: 279175 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 2.7361. Min Range: -2.7361

Max Act: 2.3630. Min Act: -0.0000

Data Index: 173580 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 2.7361. Min Range: -2.7361

Max Act: 2.2347. Min Act: -0.0000

Data Index: 549736 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 2.7361. Min Range: -2.7361

Max Act: 2.2300. Min Act: -0.0000

Data Index: 1180513 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 2.7361. Min Range: -2.7361

Max Act: 2.2144. Min Act: -0.0000

Data Index: 132849 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 2.7361. Min Range: -2.7361

Max Act: 2.2051. Min Act: -0.0000

Data Index: 604960 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 2.7361. Min Range: -2.7361

Max Act: 2.0818. Min Act: -0.0000

Data Index: 38722 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 2.7361. Min Range: -2.7361

Max Act: 1.9752. Min Act: -0.0000

Data Index: 1609586 (Python Code)

Max Activating Token Index: 719

Text #11

Max Range: 2.7361. Min Range: -2.7361

Max Act: 2.1528. Min Act: -0.0000

Data Index: 989858 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 2.7361. Min Range: -2.7361

Max Act: 2.0128. Min Act: -0.0000

Data Index: 1505115 (Python Code)

Max Activating Token Index: 327

Text #13

Max Range: 2.7361. Min Range: -2.7361

Max Act: 2.1222. Min Act: -0.0000

Data Index: 1178492 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 2.7361. Min Range: -2.7361

Max Act: 2.1042. Min Act: -0.0000

Data Index: 1486897 (Python Code)

Max Activating Token Index: 385

Text #15

Max Range: 2.7361. Min Range: -2.7361

Max Act: 2.0829. Min Act: -0.0000

Data Index: 1538011 (Python Code)

Max Activating Token Index: 76

Text #16

Max Range: 2.7361. Min Range: -2.7361

Max Act: 2.0869. Min Act: -0.0000

Data Index: 1448458 (Python Code)

Max Activating Token Index: 391

Text #17

Max Range: 2.7361. Min Range: -2.7361

Max Act: 1.9806. Min Act: -0.0000

Data Index: 1387448 (Python Code)

Max Activating Token Index: 39

Text #18

Max Range: 2.7361. Min Range: -2.7361

Max Act: 1.9498. Min Act: -0.0000

Data Index: 750966 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 2.7361. Min Range: -2.7361

Max Act: 2.0560. Min Act: -0.0000

Data Index: 56878 (C4 (Web Text))

Max Activating Token Index: 750