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

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

Neuron 179 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.1247. Min Act: -0.0001

Data Index: 1190454 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0870. Min Act: -0.0001

Data Index: 504891 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.1056. Min Act: -0.0001

Data Index: 1608239 (Python Code)

Max Activating Token Index: 775

Text #3

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.1038. Min Act: -0.0001

Data Index: 926116 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0984. Min Act: -0.0001

Data Index: 1012085 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0944. Min Act: -0.0001

Data Index: 86340 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0902. Min Act: -0.0001

Data Index: 1598868 (Python Code)

Max Activating Token Index: 147

Text #7

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0850. Min Act: -0.0001

Data Index: 710017 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0841. Min Act: -0.0001

Data Index: 186088 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0838. Min Act: -0.0001

Data Index: 1604294 (Python Code)

Max Activating Token Index: 986

Text #10

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0822. Min Act: -0.0001

Data Index: 1615927 (Python Code)

Max Activating Token Index: 611

Text #11

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0755. Min Act: -0.0001

Data Index: 362805 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0738. Min Act: -0.0001

Data Index: 994041 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0780. Min Act: -0.0001

Data Index: 386003 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1515010 (Python Code)

Max Activating Token Index: 806

Text #15

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0728. Min Act: -0.0001

Data Index: 1437193 (Python Code)

Max Activating Token Index: 868

Text #16

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0755. Min Act: -0.0001

Data Index: 141574 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0645. Min Act: -0.0001

Data Index: 1563406 (Python Code)

Max Activating Token Index: 464

Text #18

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0720. Min Act: -0.0001

Data Index: 641041 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0693. Min Act: -0.0001

Data Index: 1505639 (Python Code)

Max Activating Token Index: 646