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

Dataset: The Pile

Neuron 576 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.9080. Min Act: -0.0000

Data Index: 53851 (The Pile)

Max Activating Token Index: 837

Text #1

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.8777. Min Act: -0.0000

Data Index: 575664 (The Pile)

Max Activating Token Index: 505

Text #2

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.6492. Min Act: -0.0000

Data Index: 1467774 (The Pile)

Max Activating Token Index: 117

Text #3

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.7073. Min Act: -0.0000

Data Index: 1502340 (The Pile)

Max Activating Token Index: 773

Text #4

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.6913. Min Act: -0.0000

Data Index: 1849494 (The Pile)

Max Activating Token Index: 593

Text #5

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.6137. Min Act: -0.0000

Data Index: 665012 (The Pile)

Max Activating Token Index: 65

Text #6

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.6808. Min Act: -0.0000

Data Index: 261034 (The Pile)

Max Activating Token Index: 194

Text #7

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.6107. Min Act: -0.0000

Data Index: 77367 (The Pile)

Max Activating Token Index: 357

Text #8

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1278342 (The Pile)

Max Activating Token Index: 491

Text #9

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.6452. Min Act: -0.0000

Data Index: 496319 (The Pile)

Max Activating Token Index: 193

Text #10

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.6175. Min Act: -0.0000

Data Index: 1671859 (The Pile)

Max Activating Token Index: 479

Text #11

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.5212. Min Act: -0.0000

Data Index: 111348 (The Pile)

Max Activating Token Index: 799

Text #12

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.5891. Min Act: -0.0000

Data Index: 149073 (The Pile)

Max Activating Token Index: 815

Text #13

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.6043. Min Act: -0.0000

Data Index: 643965 (The Pile)

Max Activating Token Index: 499

Text #14

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.5662. Min Act: -0.0000

Data Index: 810145 (The Pile)

Max Activating Token Index: 332

Text #15

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.6224. Min Act: -0.0000

Data Index: 1981511 (The Pile)

Max Activating Token Index: 882

Text #16

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.5759. Min Act: -0.0000

Data Index: 1992845 (The Pile)

Max Activating Token Index: 874

Text #17

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.6257. Min Act: -0.0000

Data Index: 694649 (The Pile)

Max Activating Token Index: 491

Text #18

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.5448. Min Act: -0.0000

Data Index: 282030 (The Pile)

Max Activating Token Index: 507

Text #19

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.6166. Min Act: -0.0000

Data Index: 1844955 (The Pile)

Max Activating Token Index: 626