Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1624 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.1016. Min Act: -0.0001

Data Index: 250797 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.1012. Min Act: -0.0001

Data Index: 133076 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0961. Min Act: -0.0001

Data Index: 274764 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0998. Min Act: -0.0001

Data Index: 1111469 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0973. Min Act: -0.0001

Data Index: 559283 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.1005. Min Act: -0.0001

Data Index: 183711 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0935. Min Act: -0.0001

Data Index: 1408967 (Python Code)

Max Activating Token Index: 551

Text #7

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0953. Min Act: -0.0001

Data Index: 949086 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0988. Min Act: -0.0001

Data Index: 67822 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0958. Min Act: -0.0001

Data Index: 1377299 (Python Code)

Max Activating Token Index: 682

Text #10

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.1033. Min Act: -0.0001

Data Index: 78974 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0926. Min Act: -0.0001

Data Index: 958986 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0946. Min Act: -0.0001

Data Index: 539781 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0916. Min Act: -0.0001

Data Index: 1557029 (Python Code)

Max Activating Token Index: 524

Text #14

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0972. Min Act: -0.0001

Data Index: 1515019 (Python Code)

Max Activating Token Index: 669

Text #15

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1408645 (Python Code)

Max Activating Token Index: 744

Text #16

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0950. Min Act: -0.0001

Data Index: 483290 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0860. Min Act: -0.0001

Data Index: 1331420 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0888. Min Act: -0.0001

Data Index: 118076 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0924. Min Act: -0.0001

Data Index: 154702 (C4 (Web Text))

Max Activating Token Index: 1003