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

Dataset: The Pile

Neuron 1554 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.7679. Min Act: -0.0000

Data Index: 239205 (The Pile)

Max Activating Token Index: 348

Text #1

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.7313. Min Act: -0.0000

Data Index: 1276100 (The Pile)

Max Activating Token Index: 532

Text #2

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.6916. Min Act: -0.0000

Data Index: 1417188 (The Pile)

Max Activating Token Index: 702

Text #3

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.6845. Min Act: -0.0000

Data Index: 514772 (The Pile)

Max Activating Token Index: 987

Text #4

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.6854. Min Act: -0.0000

Data Index: 856551 (The Pile)

Max Activating Token Index: 417

Text #5

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1554959 (The Pile)

Max Activating Token Index: 334

Text #6

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.6227. Min Act: -0.0000

Data Index: 43882 (The Pile)

Max Activating Token Index: 868

Text #7

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.6152. Min Act: -0.0000

Data Index: 568561 (The Pile)

Max Activating Token Index: 556

Text #8

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.6295. Min Act: -0.0000

Data Index: 238480 (The Pile)

Max Activating Token Index: 964

Text #9

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.5641. Min Act: -0.0000

Data Index: 1845732 (The Pile)

Max Activating Token Index: 834

Text #10

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.5843. Min Act: -0.0000

Data Index: 1725289 (The Pile)

Max Activating Token Index: 1009

Text #11

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.5981. Min Act: -0.0000

Data Index: 1990201 (The Pile)

Max Activating Token Index: 252

Text #12

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.5903. Min Act: -0.0000

Data Index: 1254472 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.5897. Min Act: -0.0000

Data Index: 527796 (The Pile)

Max Activating Token Index: 689

Text #14

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.5645. Min Act: -0.0000

Data Index: 1319174 (The Pile)

Max Activating Token Index: 325

Text #15

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.5968. Min Act: -0.0000

Data Index: 1479242 (The Pile)

Max Activating Token Index: 346

Text #16

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.5145. Min Act: -0.0000

Data Index: 1087059 (The Pile)

Max Activating Token Index: 734

Text #17

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.6093. Min Act: -0.0000

Data Index: 270744 (The Pile)

Max Activating Token Index: 101

Text #18

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.5274. Min Act: -0.0000

Data Index: 995098 (The Pile)

Max Activating Token Index: 910

Text #19

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.5553. Min Act: -0.0000

Data Index: 482582 (The Pile)

Max Activating Token Index: 727