Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3642 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.3015. Min Act: -0.0000

Data Index: 473016 (The Pile)

Max Activating Token Index: 433

Text #1

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1222807 (The Pile)

Max Activating Token Index: 421

Text #2

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.2256. Min Act: -0.0000

Data Index: 267260 (The Pile)

Max Activating Token Index: 54

Text #3

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.2613. Min Act: -0.0000

Data Index: 1462596 (The Pile)

Max Activating Token Index: 335

Text #4

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.2433. Min Act: -0.0000

Data Index: 1451380 (The Pile)

Max Activating Token Index: 463

Text #5

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1409843 (The Pile)

Max Activating Token Index: 219

Text #6

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.2253. Min Act: -0.0000

Data Index: 1044641 (The Pile)

Max Activating Token Index: 581

Text #7

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.2189. Min Act: -0.0000

Data Index: 1601756 (The Pile)

Max Activating Token Index: 574

Text #8

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.2383. Min Act: -0.0000

Data Index: 1710578 (The Pile)

Max Activating Token Index: 815

Text #9

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.2009. Min Act: -0.0000

Data Index: 149037 (The Pile)

Max Activating Token Index: 16

Text #10

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.2150. Min Act: -0.0000

Data Index: 1717404 (The Pile)

Max Activating Token Index: 894

Text #11

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.2144. Min Act: -0.0000

Data Index: 1037678 (The Pile)

Max Activating Token Index: 146

Text #12

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.2351. Min Act: -0.0000

Data Index: 907815 (The Pile)

Max Activating Token Index: 406

Text #13

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.2171. Min Act: -0.0000

Data Index: 563937 (The Pile)

Max Activating Token Index: 824

Text #14

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.1862. Min Act: -0.0000

Data Index: 1208442 (The Pile)

Max Activating Token Index: 629

Text #15

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.1881. Min Act: -0.0000

Data Index: 1864003 (The Pile)

Max Activating Token Index: 237

Text #16

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.2082. Min Act: -0.0000

Data Index: 1503907 (The Pile)

Max Activating Token Index: 293

Text #17

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.1724. Min Act: -0.0000

Data Index: 1465697 (The Pile)

Max Activating Token Index: 879

Text #18

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.2192. Min Act: -0.0000

Data Index: 371820 (The Pile)

Max Activating Token Index: 56

Text #19

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.1961. Min Act: -0.0000

Data Index: 21198 (The Pile)

Max Activating Token Index: 163