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

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

Neuron 3956 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2585. Min Act: -0.0000

Data Index: 234376 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2182. Min Act: -0.0000

Data Index: 247606 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2073. Min Act: 0.0000

Data Index: 532110 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1951. Min Act: -0.0000

Data Index: 900925 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1822. Min Act: -0.0000

Data Index: 159992 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1879. Min Act: -0.0000

Data Index: 196033 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1832. Min Act: -0.0000

Data Index: 213447 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1794. Min Act: -0.0000

Data Index: 649132 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1781. Min Act: -0.0000

Data Index: 63197 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1719. Min Act: -0.0001

Data Index: 1101487 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1775. Min Act: 0.0001

Data Index: 1084687 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1754. Min Act: -0.0000

Data Index: 10940 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1764. Min Act: -0.0000

Data Index: 1123053 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1750. Min Act: -0.0000

Data Index: 277994 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1703. Min Act: -0.0000

Data Index: 595914 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1766. Min Act: -0.0000

Data Index: 1324715 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1688. Min Act: -0.0000

Data Index: 358255 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1687. Min Act: -0.0001

Data Index: 880975 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1680. Min Act: -0.0000

Data Index: 591734 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1651. Min Act: -0.0000

Data Index: 590348 (C4 (Web Text))

Max Activating Token Index: 760