Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 207 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0985. Min Act: -0.0001

Data Index: 310322 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0814. Min Act: -0.0002

Data Index: 1042914 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0845. Min Act: -0.0002

Data Index: 173693 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0803. Min Act: -0.0001

Data Index: 495981 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0751. Min Act: -0.0001

Data Index: 919677 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0725. Min Act: -0.0002

Data Index: 390812 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0758. Min Act: -0.0002

Data Index: 574664 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0832. Min Act: -0.0002

Data Index: 335939 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0795. Min Act: -0.0002

Data Index: 991907 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0800. Min Act: -0.0002

Data Index: 738619 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0843. Min Act: -0.0002

Data Index: 418499 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0678. Min Act: -0.0002

Data Index: 631759 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1313553 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0755. Min Act: -0.0002

Data Index: 624948 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0699. Min Act: -0.0001

Data Index: 946510 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0682. Min Act: -0.0001

Data Index: 1595188 (Python Code)

Max Activating Token Index: 54

Text #16

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0754. Min Act: -0.0002

Data Index: 656591 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0747. Min Act: -0.0002

Data Index: 605266 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0777. Min Act: -0.0001

Data Index: 358975 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0717. Min Act: -0.0002

Data Index: 343017 (C4 (Web Text))

Max Activating Token Index: 254