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

Dataset: The Pile

Neuron 130 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0254. Min Act: -0.0000

Data Index: 713363 (The Pile)

Max Activating Token Index: 397

Text #1

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0101. Min Act: -0.0000

Data Index: 217100 (The Pile)

Max Activating Token Index: 1010

Text #2

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0107. Min Act: -0.0000

Data Index: 709532 (The Pile)

Max Activating Token Index: 679

Text #3

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0187. Min Act: -0.0000

Data Index: 853605 (The Pile)

Max Activating Token Index: 699

Text #4

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0053. Min Act: -0.0000

Data Index: 1025127 (The Pile)

Max Activating Token Index: 172

Text #5

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0045. Min Act: -0.0000

Data Index: 1268162 (The Pile)

Max Activating Token Index: 685

Text #6

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0036. Min Act: -0.0000

Data Index: 157812 (The Pile)

Max Activating Token Index: 354

Text #7

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0056. Min Act: -0.0000

Data Index: 1593721 (The Pile)

Max Activating Token Index: 720

Text #8

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0107. Min Act: -0.0000

Data Index: 1275806 (The Pile)

Max Activating Token Index: 858

Text #9

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0032. Min Act: -0.0000

Data Index: 614019 (The Pile)

Max Activating Token Index: 63

Text #10

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0060. Min Act: -0.0000

Data Index: 115420 (The Pile)

Max Activating Token Index: 61

Text #11

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0051. Min Act: -0.0000

Data Index: 686296 (The Pile)

Max Activating Token Index: 699

Text #12

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0049. Min Act: -0.0000

Data Index: 1673048 (The Pile)

Max Activating Token Index: 780

Text #13

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0036. Min Act: -0.0000

Data Index: 1785639 (The Pile)

Max Activating Token Index: 500

Text #14

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0043. Min Act: -0.0000

Data Index: 737353 (The Pile)

Max Activating Token Index: 392

Text #15

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0042. Min Act: -0.0000

Data Index: 1771521 (The Pile)

Max Activating Token Index: 583

Text #16

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0041. Min Act: -0.0000

Data Index: 454067 (The Pile)

Max Activating Token Index: 660

Text #17

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0037. Min Act: -0.0000

Data Index: 1146875 (The Pile)

Max Activating Token Index: 609

Text #18

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0042. Min Act: -0.0001

Data Index: 476293 (The Pile)

Max Activating Token Index: 828

Text #19

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0044. Min Act: -0.0000

Data Index: 20144 (The Pile)

Max Activating Token Index: 565