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

Dataset: The Pile

Neuron 693 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: 0.8067. Min Range: -0.8067

Max Act: 0.8067. Min Act: -0.0000

Data Index: 970681 (The Pile)

Max Activating Token Index: 96

Text #1

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.6709. Min Act: -0.0000

Data Index: 1121806 (The Pile)

Max Activating Token Index: 451

Text #2

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.6031. Min Act: -0.0000

Data Index: 782369 (The Pile)

Max Activating Token Index: 248

Text #3

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.4844. Min Act: -0.0000

Data Index: 1223046 (The Pile)

Max Activating Token Index: 538

Text #4

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5432. Min Act: -0.0000

Data Index: 1709771 (The Pile)

Max Activating Token Index: 332

Text #5

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.4976. Min Act: -0.0000

Data Index: 17505 (The Pile)

Max Activating Token Index: 734

Text #6

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5358. Min Act: -0.0000

Data Index: 1483899 (The Pile)

Max Activating Token Index: 551

Text #7

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5285. Min Act: -0.0000

Data Index: 720412 (The Pile)

Max Activating Token Index: 141

Text #8

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5579. Min Act: -0.0000

Data Index: 733092 (The Pile)

Max Activating Token Index: 827

Text #9

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5004. Min Act: -0.0000

Data Index: 703447 (The Pile)

Max Activating Token Index: 383

Text #10

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.4478. Min Act: -0.0000

Data Index: 1847305 (The Pile)

Max Activating Token Index: 606

Text #11

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5232. Min Act: -0.0000

Data Index: 1366657 (The Pile)

Max Activating Token Index: 957

Text #12

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5084. Min Act: -0.0000

Data Index: 972618 (The Pile)

Max Activating Token Index: 704

Text #13

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5247. Min Act: -0.0000

Data Index: 1805582 (The Pile)

Max Activating Token Index: 131

Text #14

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.4991. Min Act: -0.0000

Data Index: 1694218 (The Pile)

Max Activating Token Index: 716

Text #15

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.4662. Min Act: -0.0000

Data Index: 431731 (The Pile)

Max Activating Token Index: 322

Text #16

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5260. Min Act: -0.0000

Data Index: 878767 (The Pile)

Max Activating Token Index: 577

Text #17

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.4874. Min Act: -0.0000

Data Index: 1187105 (The Pile)

Max Activating Token Index: 782

Text #18

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.4584. Min Act: -0.0000

Data Index: 744360 (The Pile)

Max Activating Token Index: 932

Text #19

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.4867. Min Act: -0.0000

Data Index: 1102478 (The Pile)

Max Activating Token Index: 321