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

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

Neuron 2935 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: 0.8629. Min Range: -0.8629

Max Act: 0.8629. Min Act: -0.0000

Data Index: 1496895 (Python Code)

Max Activating Token Index: 942

Text #1

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1529640 (Python Code)

Max Activating Token Index: 824

Text #2

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6457. Min Act: -0.0000

Data Index: 1392940 (Python Code)

Max Activating Token Index: 949

Text #3

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6852. Min Act: -0.0000

Data Index: 1478981 (Python Code)

Max Activating Token Index: 573

Text #4

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6817. Min Act: -0.0000

Data Index: 1607756 (Python Code)

Max Activating Token Index: 208

Text #5

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1654114 (Python Code)

Max Activating Token Index: 409

Text #6

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6576. Min Act: -0.0000

Data Index: 1387991 (Python Code)

Max Activating Token Index: 721

Text #7

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1544101 (Python Code)

Max Activating Token Index: 319

Text #8

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6139. Min Act: -0.0000

Data Index: 1562381 (Python Code)

Max Activating Token Index: 139

Text #9

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6326. Min Act: -0.0000

Data Index: 1612346 (Python Code)

Max Activating Token Index: 693

Text #10

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5888. Min Act: -0.0000

Data Index: 1453836 (Python Code)

Max Activating Token Index: 285

Text #11

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1428098 (Python Code)

Max Activating Token Index: 643

Text #12

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5714. Min Act: -0.0000

Data Index: 1610774 (Python Code)

Max Activating Token Index: 852

Text #13

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1642748 (Python Code)

Max Activating Token Index: 479

Text #14

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6164. Min Act: -0.0000

Data Index: 1414360 (Python Code)

Max Activating Token Index: 292

Text #15

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5759. Min Act: -0.0000

Data Index: 1583360 (Python Code)

Max Activating Token Index: 86

Text #16

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1646288 (Python Code)

Max Activating Token Index: 464

Text #17

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5693. Min Act: -0.0001

Data Index: 1449864 (Python Code)

Max Activating Token Index: 235

Text #18

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5688. Min Act: -0.0000

Data Index: 1455683 (Python Code)

Max Activating Token Index: 157

Text #19

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5324. Min Act: -0.0000

Data Index: 1621060 (Python Code)

Max Activating Token Index: 841