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

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

Neuron 3094 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: 1.3798. Min Range: -1.3798

Max Act: 1.3478. Min Act: -0.0001

Data Index: 1113299 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.3747. Min Act: -0.0001

Data Index: 387354 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.3798. Min Act: -0.0001

Data Index: 700911 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.2741. Min Act: -0.0001

Data Index: 740755 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.3403. Min Act: -0.0001

Data Index: 1061293 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.2985. Min Act: -0.0001

Data Index: 756620 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.2705. Min Act: -0.0001

Data Index: 180190 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.2644. Min Act: -0.0001

Data Index: 1034971 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1975. Min Act: -0.0001

Data Index: 827990 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.2179. Min Act: -0.0001

Data Index: 444148 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.2769. Min Act: -0.0001

Data Index: 802812 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1976. Min Act: -0.0001

Data Index: 544737 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.3002. Min Act: -0.0001

Data Index: 401106 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.2222. Min Act: -0.0001

Data Index: 329696 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.2219. Min Act: -0.0001

Data Index: 207912 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1824. Min Act: -0.0001

Data Index: 310618 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1714. Min Act: -0.0001

Data Index: 1012705 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1097. Min Act: -0.0001

Data Index: 146927 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1022. Min Act: -0.0001

Data Index: 515374 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.2306. Min Act: -0.0001

Data Index: 256729 (C4 (Web Text))

Max Activating Token Index: 386