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

Dataset: The Pile

Neuron 1773 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: 0.1391. Min Range: -0.1391

Max Act: 0.1391. Min Act: -0.0000

Data Index: 1067740 (The Pile)

Max Activating Token Index: 48

Text #1

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1325. Min Act: -0.0000

Data Index: 271950 (The Pile)

Max Activating Token Index: 933

Text #2

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1256. Min Act: -0.0000

Data Index: 1690727 (The Pile)

Max Activating Token Index: 302

Text #3

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1147. Min Act: -0.0000

Data Index: 1710681 (The Pile)

Max Activating Token Index: 978

Text #4

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1205. Min Act: -0.0000

Data Index: 1648539 (The Pile)

Max Activating Token Index: 346

Text #5

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1215. Min Act: -0.0000

Data Index: 30104 (The Pile)

Max Activating Token Index: 782

Text #6

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1131. Min Act: -0.0000

Data Index: 1886886 (The Pile)

Max Activating Token Index: 354

Text #7

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1118. Min Act: -0.0000

Data Index: 1125730 (The Pile)

Max Activating Token Index: 819

Text #8

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1037. Min Act: -0.0000

Data Index: 654489 (The Pile)

Max Activating Token Index: 199

Text #9

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1105. Min Act: -0.0000

Data Index: 1811484 (The Pile)

Max Activating Token Index: 171

Text #10

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1052. Min Act: -0.0000

Data Index: 565102 (The Pile)

Max Activating Token Index: 873

Text #11

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1069. Min Act: -0.0000

Data Index: 417289 (The Pile)

Max Activating Token Index: 333

Text #12

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.0977. Min Act: -0.0000

Data Index: 1675975 (The Pile)

Max Activating Token Index: 667

Text #13

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1066. Min Act: -0.0000

Data Index: 1844081 (The Pile)

Max Activating Token Index: 368

Text #14

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.0942. Min Act: -0.0000

Data Index: 1375232 (The Pile)

Max Activating Token Index: 244

Text #15

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.0984. Min Act: -0.0000

Data Index: 588431 (The Pile)

Max Activating Token Index: 297

Text #16

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.0978. Min Act: -0.0000

Data Index: 1456677 (The Pile)

Max Activating Token Index: 28

Text #17

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.0972. Min Act: -0.0000

Data Index: 1765384 (The Pile)

Max Activating Token Index: 454

Text #18

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.0937. Min Act: -0.0000

Data Index: 628456 (The Pile)

Max Activating Token Index: 585

Text #19

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.0887. Min Act: -0.0000

Data Index: 1242755 (The Pile)

Max Activating Token Index: 464