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

Dataset: The Pile

Neuron 2531 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.5147. Min Act: -0.0000

Data Index: 1263279 (The Pile)

Max Activating Token Index: 722

Text #1

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.3013. Min Act: -0.0000

Data Index: 421781 (The Pile)

Max Activating Token Index: 653

Text #2

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.2148. Min Act: -0.0000

Data Index: 149409 (The Pile)

Max Activating Token Index: 392

Text #3

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.3717. Min Act: -0.0000

Data Index: 394265 (The Pile)

Max Activating Token Index: 905

Text #4

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.1422. Min Act: -0.0000

Data Index: 70493 (The Pile)

Max Activating Token Index: 396

Text #5

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.0263. Min Act: 0.0000

Data Index: 1898936 (The Pile)

Max Activating Token Index: 261

Text #6

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.2123. Min Act: -0.0000

Data Index: 518400 (The Pile)

Max Activating Token Index: 732

Text #7

Max Range: 1.5147. Min Range: -1.5147

Max Act: 0.9662. Min Act: -0.0000

Data Index: 1026033 (The Pile)

Max Activating Token Index: 489

Text #8

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.1390. Min Act: -0.0000

Data Index: 1732691 (The Pile)

Max Activating Token Index: 641

Text #9

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.0683. Min Act: -0.0000

Data Index: 1503118 (The Pile)

Max Activating Token Index: 716

Text #10

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.0838. Min Act: 0.0001

Data Index: 1918823 (The Pile)

Max Activating Token Index: 590

Text #11

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.0562. Min Act: -0.0000

Data Index: 495001 (The Pile)

Max Activating Token Index: 34

Text #12

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.1194. Min Act: 0.0000

Data Index: 464642 (The Pile)

Max Activating Token Index: 925

Text #13

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.1041. Min Act: -0.0000

Data Index: 1123790 (The Pile)

Max Activating Token Index: 598

Text #14

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.0504. Min Act: -0.0000

Data Index: 661584 (The Pile)

Max Activating Token Index: 492

Text #15

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.0166. Min Act: -0.0000

Data Index: 789144 (The Pile)

Max Activating Token Index: 365

Text #16

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.0440. Min Act: -0.0000

Data Index: 1721700 (The Pile)

Max Activating Token Index: 167

Text #17

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.0315. Min Act: -0.0000

Data Index: 1043079 (The Pile)

Max Activating Token Index: 142

Text #18

Max Range: 1.5147. Min Range: -1.5147

Max Act: 0.9073. Min Act: -0.0000

Data Index: 1032965 (The Pile)

Max Activating Token Index: 71

Text #19

Max Range: 1.5147. Min Range: -1.5147

Max Act: 0.9944. Min Act: -0.0000

Data Index: 1483551 (The Pile)

Max Activating Token Index: 287