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

Dataset: The Pile

Neuron 4888 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: 1.7216. Min Range: -1.7216

Max Act: 1.7216. Min Act: -0.0000

Data Index: 1740079 (The Pile)

Max Activating Token Index: 140

Text #1

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.6053. Min Act: -0.0000

Data Index: 1193700 (The Pile)

Max Activating Token Index: 766

Text #2

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.6768. Min Act: -0.0000

Data Index: 37150 (The Pile)

Max Activating Token Index: 552

Text #3

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.5928. Min Act: -0.0000

Data Index: 1563139 (The Pile)

Max Activating Token Index: 992

Text #4

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.6553. Min Act: -0.0000

Data Index: 1930910 (The Pile)

Max Activating Token Index: 794

Text #5

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.5170. Min Act: -0.0000

Data Index: 1621669 (The Pile)

Max Activating Token Index: 383

Text #6

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.6064. Min Act: -0.0000

Data Index: 1246851 (The Pile)

Max Activating Token Index: 458

Text #7

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.5780. Min Act: -0.0000

Data Index: 1247399 (The Pile)

Max Activating Token Index: 427

Text #8

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.5785. Min Act: -0.0000

Data Index: 507411 (The Pile)

Max Activating Token Index: 696

Text #9

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.4876. Min Act: -0.0000

Data Index: 367494 (The Pile)

Max Activating Token Index: 676

Text #10

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.5735. Min Act: -0.0000

Data Index: 1566157 (The Pile)

Max Activating Token Index: 163

Text #11

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.4909. Min Act: -0.0000

Data Index: 70389 (The Pile)

Max Activating Token Index: 994

Text #12

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.4545. Min Act: -0.0000

Data Index: 1900125 (The Pile)

Max Activating Token Index: 449

Text #13

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.5196. Min Act: -0.0000

Data Index: 1487669 (The Pile)

Max Activating Token Index: 176

Text #14

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.5171. Min Act: -0.0000

Data Index: 730534 (The Pile)

Max Activating Token Index: 264

Text #15

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.5108. Min Act: -0.0000

Data Index: 228875 (The Pile)

Max Activating Token Index: 439

Text #16

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.3171. Min Act: -0.0000

Data Index: 1143434 (The Pile)

Max Activating Token Index: 827

Text #17

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.5747. Min Act: -0.0000

Data Index: 944473 (The Pile)

Max Activating Token Index: 713

Text #18

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.4362. Min Act: -0.0000

Data Index: 433584 (The Pile)

Max Activating Token Index: 151

Text #19

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.4258. Min Act: -0.0000

Data Index: 1842407 (The Pile)

Max Activating Token Index: 1016