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

Dataset: The Pile

Neuron 137 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: 1.3258. Min Range: -1.3258

Max Act: 1.3258. Min Act: -0.0000

Data Index: 1281159 (The Pile)

Max Activating Token Index: 882

Text #1

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.2603. Min Act: -0.0000

Data Index: 410322 (The Pile)

Max Activating Token Index: 570

Text #2

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.3222. Min Act: -0.0000

Data Index: 1066620 (The Pile)

Max Activating Token Index: 303

Text #3

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.3186. Min Act: -0.0000

Data Index: 1217332 (The Pile)

Max Activating Token Index: 511

Text #4

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.1909. Min Act: -0.0000

Data Index: 375658 (The Pile)

Max Activating Token Index: 919

Text #5

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.1923. Min Act: -0.0000

Data Index: 974994 (The Pile)

Max Activating Token Index: 130

Text #6

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.1656. Min Act: -0.0000

Data Index: 1674938 (The Pile)

Max Activating Token Index: 164

Text #7

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.1283. Min Act: -0.0000

Data Index: 313737 (The Pile)

Max Activating Token Index: 712

Text #8

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.1783. Min Act: -0.0000

Data Index: 1865380 (The Pile)

Max Activating Token Index: 558

Text #9

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.2112. Min Act: -0.0000

Data Index: 313541 (The Pile)

Max Activating Token Index: 429

Text #10

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.2931. Min Act: -0.0000

Data Index: 305029 (The Pile)

Max Activating Token Index: 333

Text #11

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.1616. Min Act: -0.0000

Data Index: 488214 (The Pile)

Max Activating Token Index: 235

Text #12

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.1148. Min Act: -0.0000

Data Index: 1972972 (The Pile)

Max Activating Token Index: 234

Text #13

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.1567. Min Act: -0.0000

Data Index: 440869 (The Pile)

Max Activating Token Index: 81

Text #14

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.0046. Min Act: -0.0000

Data Index: 814627 (The Pile)

Max Activating Token Index: 275

Text #15

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.0864. Min Act: -0.0000

Data Index: 1594578 (The Pile)

Max Activating Token Index: 623

Text #16

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.0706. Min Act: -0.0000

Data Index: 1137490 (The Pile)

Max Activating Token Index: 100

Text #17

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.1007. Min Act: -0.0000

Data Index: 197713 (The Pile)

Max Activating Token Index: 894

Text #18

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.0237. Min Act: -0.0000

Data Index: 1123479 (The Pile)

Max Activating Token Index: 614

Text #19

Max Range: 1.3258. Min Range: -1.3258

Max Act: 1.0812. Min Act: -0.0000

Data Index: 233921 (The Pile)

Max Activating Token Index: 457