Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 902 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6842. Min Act: -0.0000

Data Index: 677430 (The Pile)

Max Activating Token Index: 223

Text #1

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6351. Min Act: -0.0000

Data Index: 1584389 (The Pile)

Max Activating Token Index: 182

Text #2

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.7303. Min Act: -0.0000

Data Index: 512713 (The Pile)

Max Activating Token Index: 193

Text #3

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6059. Min Act: -0.0000

Data Index: 1053109 (The Pile)

Max Activating Token Index: 242

Text #4

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6670. Min Act: -0.0000

Data Index: 860693 (The Pile)

Max Activating Token Index: 381

Text #5

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6466. Min Act: -0.0000

Data Index: 606001 (The Pile)

Max Activating Token Index: 272

Text #6

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6420. Min Act: -0.0000

Data Index: 937080 (The Pile)

Max Activating Token Index: 264

Text #7

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6158. Min Act: -0.0000

Data Index: 847748 (The Pile)

Max Activating Token Index: 747

Text #8

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1479067 (The Pile)

Max Activating Token Index: 831

Text #9

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6568. Min Act: -0.0000

Data Index: 470479 (The Pile)

Max Activating Token Index: 687

Text #10

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.7166. Min Act: -0.0000

Data Index: 625244 (The Pile)

Max Activating Token Index: 192

Text #11

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1081459 (The Pile)

Max Activating Token Index: 473

Text #12

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6683. Min Act: -0.0000

Data Index: 770246 (The Pile)

Max Activating Token Index: 387

Text #13

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6159. Min Act: -0.0000

Data Index: 1387193 (The Pile)

Max Activating Token Index: 299

Text #14

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5906. Min Act: -0.0000

Data Index: 1708297 (The Pile)

Max Activating Token Index: 475

Text #15

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5592. Min Act: -0.0000

Data Index: 1748204 (The Pile)

Max Activating Token Index: 460

Text #16

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6104. Min Act: -0.0000

Data Index: 617596 (The Pile)

Max Activating Token Index: 767

Text #17

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1144583 (The Pile)

Max Activating Token Index: 234

Text #18

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5732. Min Act: -0.0000

Data Index: 611821 (The Pile)

Max Activating Token Index: 24

Text #19

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.4931. Min Act: -0.0000

Data Index: 1891933 (The Pile)

Max Activating Token Index: 961