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

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

Neuron 3324 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.1015. Min Act: -0.0001

Data Index: 1573418 (Python Code)

Max Activating Token Index: 221

Text #1

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0828. Min Act: -0.0001

Data Index: 1170724 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0763. Min Act: -0.0001

Data Index: 1244937 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0759. Min Act: -0.0001

Data Index: 654886 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0718. Min Act: -0.0001

Data Index: 990895 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0676. Min Act: -0.0001

Data Index: 669333 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0700. Min Act: -0.0001

Data Index: 222906 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0650. Min Act: -0.0001

Data Index: 1019525 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0690. Min Act: -0.0001

Data Index: 339311 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0677. Min Act: -0.0001

Data Index: 1258911 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0568. Min Act: -0.0001

Data Index: 1391454 (Python Code)

Max Activating Token Index: 183

Text #11

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0702. Min Act: -0.0001

Data Index: 990622 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0582. Min Act: -0.0001

Data Index: 1364965 (Python Code)

Max Activating Token Index: 316

Text #13

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1595360 (Python Code)

Max Activating Token Index: 397

Text #14

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0695. Min Act: -0.0001

Data Index: 455234 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0657. Min Act: -0.0001

Data Index: 525150 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0685. Min Act: -0.0001

Data Index: 412158 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0636. Min Act: -0.0001

Data Index: 164120 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0692. Min Act: -0.0001

Data Index: 1269216 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0615. Min Act: -0.0001

Data Index: 1632938 (Python Code)

Max Activating Token Index: 561