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

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

Neuron 255 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: 0.1094. Min Range: -0.1094

Max Act: 0.1094. Min Act: -0.0002

Data Index: 724982 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0938. Min Act: -0.0001

Data Index: 170137 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0908. Min Act: -0.0002

Data Index: 733219 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0809. Min Act: -0.0001

Data Index: 306003 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0827. Min Act: -0.0002

Data Index: 323953 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0755. Min Act: -0.0002

Data Index: 1151999 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1141818 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0850. Min Act: -0.0002

Data Index: 724404 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1082053 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0788. Min Act: -0.0002

Data Index: 19483 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0775. Min Act: -0.0002

Data Index: 295574 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1064828 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0770. Min Act: -0.0002

Data Index: 45863 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0763. Min Act: -0.0002

Data Index: 345626 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0794. Min Act: -0.0002

Data Index: 1377253 (Python Code)

Max Activating Token Index: 290

Text #15

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0817. Min Act: -0.0002

Data Index: 473589 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0746. Min Act: -0.0002

Data Index: 625176 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0808. Min Act: -0.0002

Data Index: 299285 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0753. Min Act: -0.0001

Data Index: 421476 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0712. Min Act: -0.0002

Data Index: 442318 (C4 (Web Text))

Max Activating Token Index: 826