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

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

Neuron 2821 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: 0.3832. Min Range: -0.3832

Max Act: 0.3832. Min Act: -0.0001

Data Index: 721598 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.3466. Min Act: -0.0001

Data Index: 952886 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.3113. Min Act: -0.0000

Data Index: 354268 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.3102. Min Act: -0.0001

Data Index: 1010139 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.3202. Min Act: -0.0000

Data Index: 1043302 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2989. Min Act: -0.0000

Data Index: 394068 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.3012. Min Act: -0.0000

Data Index: 614551 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.3089. Min Act: -0.0000

Data Index: 573284 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2768. Min Act: -0.0001

Data Index: 920078 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2759. Min Act: -0.0000

Data Index: 172449 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2857. Min Act: -0.0001

Data Index: 879999 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2836. Min Act: -0.0001

Data Index: 1014335 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2801. Min Act: -0.0001

Data Index: 173808 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2706. Min Act: -0.0000

Data Index: 508622 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2741. Min Act: -0.0001

Data Index: 1270680 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1356296 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2724. Min Act: -0.0000

Data Index: 1188629 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2538. Min Act: -0.0000

Data Index: 66501 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2601. Min Act: -0.0000

Data Index: 37249 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2496. Min Act: -0.0000

Data Index: 773604 (C4 (Web Text))

Max Activating Token Index: 252