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

Dataset: The Pile

Neuron 4592 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: 3.1168. Min Range: -3.1168

Max Act: 3.1168. Min Act: -0.0000

Data Index: 1351322 (The Pile)

Max Activating Token Index: 598

Text #1

Max Range: 3.1168. Min Range: -3.1168

Max Act: 2.9944. Min Act: -0.0000

Data Index: 1904173 (The Pile)

Max Activating Token Index: 205

Text #2

Max Range: 3.1168. Min Range: -3.1168

Max Act: 2.5474. Min Act: -0.0000

Data Index: 1467833 (The Pile)

Max Activating Token Index: 499

Text #3

Max Range: 3.1168. Min Range: -3.1168

Max Act: 2.5155. Min Act: -0.0000

Data Index: 1476537 (The Pile)

Max Activating Token Index: 273

Text #4

Max Range: 3.1168. Min Range: -3.1168

Max Act: 2.3001. Min Act: -0.0000

Data Index: 1127056 (The Pile)

Max Activating Token Index: 82

Text #5

Max Range: 3.1168. Min Range: -3.1168

Max Act: 2.0952. Min Act: -0.0000

Data Index: 859831 (The Pile)

Max Activating Token Index: 568

Text #6

Max Range: 3.1168. Min Range: -3.1168

Max Act: 1.8771. Min Act: -0.0000

Data Index: 1174100 (The Pile)

Max Activating Token Index: 281

Text #7

Max Range: 3.1168. Min Range: -3.1168

Max Act: 2.0338. Min Act: -0.0000

Data Index: 992010 (The Pile)

Max Activating Token Index: 69

Text #8

Max Range: 3.1168. Min Range: -3.1168

Max Act: 1.7287. Min Act: -0.0000

Data Index: 430490 (The Pile)

Max Activating Token Index: 447

Text #9

Max Range: 3.1168. Min Range: -3.1168

Max Act: 1.6388. Min Act: -0.0000

Data Index: 1831869 (The Pile)

Max Activating Token Index: 309

Text #10

Max Range: 3.1168. Min Range: -3.1168

Max Act: 1.7768. Min Act: -0.0000

Data Index: 714227 (The Pile)

Max Activating Token Index: 304

Text #11

Max Range: 3.1168. Min Range: -3.1168

Max Act: 1.6316. Min Act: -0.0000

Data Index: 293670 (The Pile)

Max Activating Token Index: 851

Text #12

Max Range: 3.1168. Min Range: -3.1168

Max Act: 1.5586. Min Act: -0.0000

Data Index: 1101280 (The Pile)

Max Activating Token Index: 620

Text #13

Max Range: 3.1168. Min Range: -3.1168

Max Act: 1.5247. Min Act: -0.0000

Data Index: 778942 (The Pile)

Max Activating Token Index: 953

Text #14

Max Range: 3.1168. Min Range: -3.1168

Max Act: 1.2741. Min Act: 0.0000

Data Index: 56563 (The Pile)

Max Activating Token Index: 655

Text #15

Max Range: 3.1168. Min Range: -3.1168

Max Act: 1.4857. Min Act: -0.0000

Data Index: 1047903 (The Pile)

Max Activating Token Index: 480

Text #16

Max Range: 3.1168. Min Range: -3.1168

Max Act: 1.4829. Min Act: -0.0000

Data Index: 742084 (The Pile)

Max Activating Token Index: 667

Text #17

Max Range: 3.1168. Min Range: -3.1168

Max Act: 1.7656. Min Act: -0.0000

Data Index: 25302 (The Pile)

Max Activating Token Index: 1012

Text #18

Max Range: 3.1168. Min Range: -3.1168

Max Act: 1.3794. Min Act: -0.0000

Data Index: 1019006 (The Pile)

Max Activating Token Index: 568

Text #19

Max Range: 3.1168. Min Range: -3.1168

Max Act: 1.0951. Min Act: 0.0000

Data Index: 164440 (The Pile)

Max Activating Token Index: 532