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

Dataset: The Pile

Neuron 55 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1164. Min Range: -1.1164

Max Act: 1.1164. Min Act: -0.0000

Data Index: 1633477 (The Pile)

Max Activating Token Index: 525

Text #1

Max Range: 1.1164. Min Range: -1.1164

Max Act: 0.9697. Min Act: -0.0000

Data Index: 108823 (The Pile)

Max Activating Token Index: 869

Text #2

Max Range: 1.1164. Min Range: -1.1164

Max Act: 1.0268. Min Act: -0.0000

Data Index: 1244292 (The Pile)

Max Activating Token Index: 305

Text #3

Max Range: 1.1164. Min Range: -1.1164

Max Act: 0.8985. Min Act: -0.0000

Data Index: 682546 (The Pile)

Max Activating Token Index: 596

Text #4

Max Range: 1.1164. Min Range: -1.1164

Max Act: 0.9140. Min Act: -0.0000

Data Index: 650867 (The Pile)

Max Activating Token Index: 792

Text #5

Max Range: 1.1164. Min Range: -1.1164

Max Act: 0.8520. Min Act: -0.0000

Data Index: 1227928 (The Pile)

Max Activating Token Index: 324

Text #6

Max Range: 1.1164. Min Range: -1.1164

Max Act: 0.8500. Min Act: -0.0000

Data Index: 1506024 (The Pile)

Max Activating Token Index: 520

Text #7

Max Range: 1.1164. Min Range: -1.1164

Max Act: 0.8853. Min Act: -0.0000

Data Index: 1263980 (The Pile)

Max Activating Token Index: 8

Text #8

Max Range: 1.1164. Min Range: -1.1164

Max Act: 0.8200. Min Act: -0.0000

Data Index: 384771 (The Pile)

Max Activating Token Index: 945

Text #9

Max Range: 1.1164. Min Range: -1.1164

Max Act: 0.8843. Min Act: -0.0000

Data Index: 1406347 (The Pile)

Max Activating Token Index: 795

Text #10

Max Range: 1.1164. Min Range: -1.1164

Max Act: 0.8376. Min Act: -0.0000

Data Index: 360789 (The Pile)

Max Activating Token Index: 354

Text #11

Max Range: 1.1164. Min Range: -1.1164

Max Act: 0.8091. Min Act: -0.0000

Data Index: 1956485 (The Pile)

Max Activating Token Index: 51

Text #12

Max Range: 1.1164. Min Range: -1.1164

Max Act: 0.8158. Min Act: -0.0000

Data Index: 806688 (The Pile)

Max Activating Token Index: 119

Text #13

Max Range: 1.1164. Min Range: -1.1164

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1129798 (The Pile)

Max Activating Token Index: 746

Text #14

Max Range: 1.1164. Min Range: -1.1164

Max Act: 0.8215. Min Act: -0.0000

Data Index: 1512267 (The Pile)

Max Activating Token Index: 1013

Text #15

Max Range: 1.1164. Min Range: -1.1164

Max Act: 0.7899. Min Act: -0.0000

Data Index: 259238 (The Pile)

Max Activating Token Index: 482

Text #16

Max Range: 1.1164. Min Range: -1.1164

Max Act: 0.7825. Min Act: -0.0000

Data Index: 742416 (The Pile)

Max Activating Token Index: 992

Text #17

Max Range: 1.1164. Min Range: -1.1164

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1382348 (The Pile)

Max Activating Token Index: 323

Text #18

Max Range: 1.1164. Min Range: -1.1164

Max Act: 0.7545. Min Act: -0.0000

Data Index: 723309 (The Pile)

Max Activating Token Index: 444

Text #19

Max Range: 1.1164. Min Range: -1.1164

Max Act: 0.8384. Min Act: -0.0000

Data Index: 92813 (The Pile)

Max Activating Token Index: 855