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

Dataset: The Pile

Neuron 2109 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.2263. Min Act: -0.0000

Data Index: 1490090 (The Pile)

Max Activating Token Index: 807

Text #1

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.1232. Min Act: -0.0000

Data Index: 1575769 (The Pile)

Max Activating Token Index: 433

Text #2

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.2134. Min Act: -0.0000

Data Index: 1165524 (The Pile)

Max Activating Token Index: 541

Text #3

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.1647. Min Act: -0.0000

Data Index: 914714 (The Pile)

Max Activating Token Index: 314

Text #4

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.0801. Min Act: -0.0000

Data Index: 1565202 (The Pile)

Max Activating Token Index: 353

Text #5

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8989. Min Act: -0.0000

Data Index: 1522940 (The Pile)

Max Activating Token Index: 876

Text #6

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9416. Min Act: 0.0001

Data Index: 558900 (The Pile)

Max Activating Token Index: 234

Text #7

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9278. Min Act: -0.0000

Data Index: 1119367 (The Pile)

Max Activating Token Index: 449

Text #8

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8644. Min Act: -0.0000

Data Index: 1884012 (The Pile)

Max Activating Token Index: 882

Text #9

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9001. Min Act: -0.0000

Data Index: 964314 (The Pile)

Max Activating Token Index: 272

Text #10

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9093. Min Act: 0.0000

Data Index: 1212842 (The Pile)

Max Activating Token Index: 874

Text #11

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8952. Min Act: -0.0000

Data Index: 1675400 (The Pile)

Max Activating Token Index: 732

Text #12

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1265095 (The Pile)

Max Activating Token Index: 303

Text #13

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8716. Min Act: -0.0000

Data Index: 1263871 (The Pile)

Max Activating Token Index: 772

Text #14

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8451. Min Act: -0.0000

Data Index: 1528497 (The Pile)

Max Activating Token Index: 88

Text #15

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8426. Min Act: -0.0000

Data Index: 224613 (The Pile)

Max Activating Token Index: 707

Text #16

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8382. Min Act: 0.0000

Data Index: 1849014 (The Pile)

Max Activating Token Index: 251

Text #17

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8343. Min Act: -0.0000

Data Index: 1143838 (The Pile)

Max Activating Token Index: 573

Text #18

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8805. Min Act: -0.0000

Data Index: 1846067 (The Pile)

Max Activating Token Index: 663

Text #19

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.7746. Min Act: -0.0000

Data Index: 833124 (The Pile)

Max Activating Token Index: 706