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

Dataset: The Pile

Neuron 1687 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1564. Min Range: -5.1564

Max Act: 5.1564. Min Act: -0.0000

Data Index: 576331 (The Pile)

Max Activating Token Index: 41

Text #1

Max Range: 5.1564. Min Range: -5.1564

Max Act: 4.6333. Min Act: -0.0000

Data Index: 1249081 (The Pile)

Max Activating Token Index: 617

Text #2

Max Range: 5.1564. Min Range: -5.1564

Max Act: 3.6307. Min Act: -0.0000

Data Index: 80983 (The Pile)

Max Activating Token Index: 792

Text #3

Max Range: 5.1564. Min Range: -5.1564

Max Act: 4.0702. Min Act: -0.0000

Data Index: 1067520 (The Pile)

Max Activating Token Index: 625

Text #4

Max Range: 5.1564. Min Range: -5.1564

Max Act: 3.5484. Min Act: -0.0000

Data Index: 1021519 (The Pile)

Max Activating Token Index: 1021

Text #5

Max Range: 5.1564. Min Range: -5.1564

Max Act: 3.8000. Min Act: -0.0000

Data Index: 296325 (The Pile)

Max Activating Token Index: 644

Text #6

Max Range: 5.1564. Min Range: -5.1564

Max Act: 3.4224. Min Act: -0.0000

Data Index: 1486257 (The Pile)

Max Activating Token Index: 120

Text #7

Max Range: 5.1564. Min Range: -5.1564

Max Act: 3.5255. Min Act: -0.0000

Data Index: 302710 (The Pile)

Max Activating Token Index: 479

Text #8

Max Range: 5.1564. Min Range: -5.1564

Max Act: 3.3659. Min Act: -0.0000

Data Index: 181 (The Pile)

Max Activating Token Index: 800

Text #9

Max Range: 5.1564. Min Range: -5.1564

Max Act: 3.3559. Min Act: -0.0000

Data Index: 1227132 (The Pile)

Max Activating Token Index: 596

Text #10

Max Range: 5.1564. Min Range: -5.1564

Max Act: 3.2382. Min Act: -0.0000

Data Index: 1861911 (The Pile)

Max Activating Token Index: 181

Text #11

Max Range: 5.1564. Min Range: -5.1564

Max Act: 3.2442. Min Act: -0.0000

Data Index: 1607398 (The Pile)

Max Activating Token Index: 196

Text #12

Max Range: 5.1564. Min Range: -5.1564

Max Act: 3.1400. Min Act: -0.0000

Data Index: 1972435 (The Pile)

Max Activating Token Index: 102

Text #13

Max Range: 5.1564. Min Range: -5.1564

Max Act: 3.0909. Min Act: -0.0000

Data Index: 10485 (The Pile)

Max Activating Token Index: 459

Text #14

Max Range: 5.1564. Min Range: -5.1564

Max Act: 2.9134. Min Act: -0.0000

Data Index: 1100269 (The Pile)

Max Activating Token Index: 197

Text #15

Max Range: 5.1564. Min Range: -5.1564

Max Act: 2.8809. Min Act: -0.0000

Data Index: 204995 (The Pile)

Max Activating Token Index: 186

Text #16

Max Range: 5.1564. Min Range: -5.1564

Max Act: 2.9035. Min Act: -0.0000

Data Index: 96123 (The Pile)

Max Activating Token Index: 65

Text #17

Max Range: 5.1564. Min Range: -5.1564

Max Act: 3.0587. Min Act: -0.0000

Data Index: 1808100 (The Pile)

Max Activating Token Index: 278

Text #18

Max Range: 5.1564. Min Range: -5.1564

Max Act: 2.7700. Min Act: -0.0000

Data Index: 1448049 (The Pile)

Max Activating Token Index: 635

Text #19

Max Range: 5.1564. Min Range: -5.1564

Max Act: 2.8393. Min Act: -0.0000

Data Index: 883804 (The Pile)

Max Activating Token Index: 303