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

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

Neuron 5084 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0862. Min Range: -2.0862

Max Act: 2.0862. Min Act: -0.0000

Data Index: 895837 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 2.0862. Min Range: -2.0862

Max Act: 1.8294. Min Act: -0.0000

Data Index: 1603811 (Python Code)

Max Activating Token Index: 942

Text #2

Max Range: 2.0862. Min Range: -2.0862

Max Act: 1.6130. Min Act: -0.0000

Data Index: 1398667 (Python Code)

Max Activating Token Index: 812

Text #3

Max Range: 2.0862. Min Range: -2.0862

Max Act: 1.6013. Min Act: -0.0000

Data Index: 1567229 (Python Code)

Max Activating Token Index: 797

Text #4

Max Range: 2.0862. Min Range: -2.0862

Max Act: 1.5828. Min Act: -0.0000

Data Index: 1391042 (Python Code)

Max Activating Token Index: 789

Text #5

Max Range: 2.0862. Min Range: -2.0862

Max Act: 1.5403. Min Act: -0.0000

Data Index: 1388333 (Python Code)

Max Activating Token Index: 883

Text #6

Max Range: 2.0862. Min Range: -2.0862

Max Act: 1.4856. Min Act: -0.0000

Data Index: 1509211 (Python Code)

Max Activating Token Index: 314

Text #7

Max Range: 2.0862. Min Range: -2.0862

Max Act: 1.5249. Min Act: -0.0000

Data Index: 343737 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 2.0862. Min Range: -2.0862

Max Act: 1.5045. Min Act: -0.0000

Data Index: 290062 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 2.0862. Min Range: -2.0862

Max Act: 1.4696. Min Act: -0.0000

Data Index: 1413222 (Python Code)

Max Activating Token Index: 838

Text #10

Max Range: 2.0862. Min Range: -2.0862

Max Act: 1.4030. Min Act: -0.0000

Data Index: 218940 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 2.0862. Min Range: -2.0862

Max Act: 1.3729. Min Act: -0.0000

Data Index: 508753 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 2.0862. Min Range: -2.0862

Max Act: 1.4110. Min Act: -0.0000

Data Index: 306456 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 2.0862. Min Range: -2.0862

Max Act: 1.3875. Min Act: -0.0000

Data Index: 642619 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 2.0862. Min Range: -2.0862

Max Act: 1.3868. Min Act: -0.0000

Data Index: 1011580 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 2.0862. Min Range: -2.0862

Max Act: 1.3312. Min Act: -0.0000

Data Index: 309670 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 2.0862. Min Range: -2.0862

Max Act: 1.2857. Min Act: -0.0000

Data Index: 924039 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 2.0862. Min Range: -2.0862

Max Act: 1.3508. Min Act: -0.0000

Data Index: 1393769 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 2.0862. Min Range: -2.0862

Max Act: 1.3424. Min Act: -0.0000

Data Index: 1595661 (Python Code)

Max Activating Token Index: 115

Text #19

Max Range: 2.0862. Min Range: -2.0862

Max Act: 1.3508. Min Act: -0.0000

Data Index: 1001050 (C4 (Web Text))

Max Activating Token Index: 465