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

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

Neuron 2017 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.1575. Min Act: -0.0000

Data Index: 1430986 (Python Code)

Max Activating Token Index: 90

Text #1

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.8593. Min Act: -0.0000

Data Index: 1491872 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.7774. Min Act: -0.0000

Data Index: 236439 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.7912. Min Act: -0.0000

Data Index: 1477573 (Python Code)

Max Activating Token Index: 149

Text #4

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.7372. Min Act: -0.0000

Data Index: 557066 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.6836. Min Act: -0.0000

Data Index: 1392977 (Python Code)

Max Activating Token Index: 359

Text #6

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.7657. Min Act: -0.0000

Data Index: 1507374 (Python Code)

Max Activating Token Index: 283

Text #7

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.7430. Min Act: -0.0000

Data Index: 1262798 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.7803. Min Act: -0.0000

Data Index: 1210446 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.7770. Min Act: -0.0000

Data Index: 878463 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.6979. Min Act: -0.0000

Data Index: 1009869 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.7037. Min Act: -0.0000

Data Index: 87731 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.6695. Min Act: -0.0000

Data Index: 1588540 (Python Code)

Max Activating Token Index: 116

Text #13

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.7094. Min Act: -0.0000

Data Index: 1235688 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.6721. Min Act: -0.0000

Data Index: 1531300 (Python Code)

Max Activating Token Index: 183

Text #15

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.6524. Min Act: -0.0000

Data Index: 29181 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.6761. Min Act: -0.0000

Data Index: 1555949 (Python Code)

Max Activating Token Index: 178

Text #17

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.6994. Min Act: -0.0000

Data Index: 1656369 (Python Code)

Max Activating Token Index: 234

Text #18

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.6639. Min Act: -0.0000

Data Index: 980788 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.6876. Min Act: -0.0000

Data Index: 1447363 (Python Code)

Max Activating Token Index: 92