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

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

Neuron 2604 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.8794. Min Act: -0.0000

Data Index: 175739 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.7614. Min Act: -0.0000

Data Index: 82913 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.7512. Min Act: -0.0000

Data Index: 520535 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.7206. Min Act: -0.0000

Data Index: 316002 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.7143. Min Act: -0.0000

Data Index: 298042 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6843. Min Act: -0.0000

Data Index: 554083 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6463. Min Act: -0.0000

Data Index: 40122 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6808. Min Act: -0.0000

Data Index: 109771 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6752. Min Act: -0.0000

Data Index: 1106903 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.7122. Min Act: -0.0001

Data Index: 1243288 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6693. Min Act: -0.0000

Data Index: 438833 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6466. Min Act: -0.0001

Data Index: 1061318 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6389. Min Act: 0.0000

Data Index: 24339 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6573. Min Act: -0.0000

Data Index: 375915 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6788. Min Act: -0.0000

Data Index: 1083491 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6365. Min Act: -0.0000

Data Index: 620267 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6596. Min Act: -0.0001

Data Index: 760017 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6569. Min Act: -0.0001

Data Index: 684695 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6357. Min Act: -0.0000

Data Index: 787789 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6555. Min Act: -0.0000

Data Index: 457490 (C4 (Web Text))

Max Activating Token Index: 440