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

Dataset: The Pile

Neuron 49 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1222. Min Act: -0.0000

Data Index: 1509967 (The Pile)

Max Activating Token Index: 1018

Text #1

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1351. Min Act: -0.0000

Data Index: 234344 (The Pile)

Max Activating Token Index: 601

Text #2

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1300. Min Act: -0.0000

Data Index: 1685563 (The Pile)

Max Activating Token Index: 531

Text #3

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1275. Min Act: -0.0000

Data Index: 992787 (The Pile)

Max Activating Token Index: 333

Text #4

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1149. Min Act: -0.0000

Data Index: 491655 (The Pile)

Max Activating Token Index: 107

Text #5

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1179. Min Act: -0.0000

Data Index: 1641477 (The Pile)

Max Activating Token Index: 319

Text #6

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1211. Min Act: -0.0000

Data Index: 1775311 (The Pile)

Max Activating Token Index: 299

Text #7

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1140. Min Act: -0.0000

Data Index: 1565847 (The Pile)

Max Activating Token Index: 490

Text #8

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1110. Min Act: -0.0000

Data Index: 835866 (The Pile)

Max Activating Token Index: 208

Text #9

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1062. Min Act: -0.0000

Data Index: 922629 (The Pile)

Max Activating Token Index: 127

Text #10

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1000. Min Act: -0.0000

Data Index: 1373194 (The Pile)

Max Activating Token Index: 851

Text #11

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1023. Min Act: -0.0000

Data Index: 885578 (The Pile)

Max Activating Token Index: 911

Text #12

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1067. Min Act: -0.0000

Data Index: 1639840 (The Pile)

Max Activating Token Index: 471

Text #13

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1015. Min Act: -0.0000

Data Index: 1134548 (The Pile)

Max Activating Token Index: 382

Text #14

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1031. Min Act: -0.0000

Data Index: 1048774 (The Pile)

Max Activating Token Index: 220

Text #15

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1038. Min Act: -0.0000

Data Index: 563903 (The Pile)

Max Activating Token Index: 475

Text #16

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0956. Min Act: -0.0000

Data Index: 839464 (The Pile)

Max Activating Token Index: 883

Text #17

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1067. Min Act: -0.0000

Data Index: 1435758 (The Pile)

Max Activating Token Index: 470

Text #18

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0957. Min Act: -0.0000

Data Index: 378591 (The Pile)

Max Activating Token Index: 858

Text #19

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1040. Min Act: -0.0000

Data Index: 1528964 (The Pile)

Max Activating Token Index: 612