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

Dataset: The Pile

Neuron 1698 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.6783. Min Act: -0.0000

Data Index: 1159643 (The Pile)

Max Activating Token Index: 765

Text #1

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.6444. Min Act: -0.0000

Data Index: 1182210 (The Pile)

Max Activating Token Index: 875

Text #2

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5989. Min Act: -0.0000

Data Index: 1332151 (The Pile)

Max Activating Token Index: 453

Text #3

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5788. Min Act: -0.0000

Data Index: 1277162 (The Pile)

Max Activating Token Index: 781

Text #4

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5219. Min Act: -0.0000

Data Index: 354644 (The Pile)

Max Activating Token Index: 707

Text #5

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5061. Min Act: -0.0000

Data Index: 1781997 (The Pile)

Max Activating Token Index: 804

Text #6

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5315. Min Act: -0.0000

Data Index: 897179 (The Pile)

Max Activating Token Index: 61

Text #7

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.4719. Min Act: -0.0000

Data Index: 1910432 (The Pile)

Max Activating Token Index: 630

Text #8

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5139. Min Act: -0.0000

Data Index: 111981 (The Pile)

Max Activating Token Index: 824

Text #9

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.4985. Min Act: -0.0000

Data Index: 635542 (The Pile)

Max Activating Token Index: 183

Text #10

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5183. Min Act: -0.0000

Data Index: 817026 (The Pile)

Max Activating Token Index: 121

Text #11

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5744. Min Act: -0.0000

Data Index: 828538 (The Pile)

Max Activating Token Index: 187

Text #12

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.4497. Min Act: -0.0000

Data Index: 386017 (The Pile)

Max Activating Token Index: 524

Text #13

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.4820. Min Act: -0.0000

Data Index: 1563949 (The Pile)

Max Activating Token Index: 804

Text #14

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.4873. Min Act: -0.0000

Data Index: 1552114 (The Pile)

Max Activating Token Index: 1021

Text #15

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1254730 (The Pile)

Max Activating Token Index: 285

Text #16

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.4470. Min Act: -0.0000

Data Index: 613909 (The Pile)

Max Activating Token Index: 927

Text #17

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.4260. Min Act: -0.0000

Data Index: 1042226 (The Pile)

Max Activating Token Index: 711

Text #18

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.3922. Min Act: -0.0000

Data Index: 1152495 (The Pile)

Max Activating Token Index: 845

Text #19

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.3986. Min Act: -0.0000

Data Index: 72534 (The Pile)

Max Activating Token Index: 850