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

Dataset: The Pile

Neuron 2954 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: 0.8311. Min Range: -0.8311

Max Act: 0.8311. Min Act: -0.0000

Data Index: 943029 (The Pile)

Max Activating Token Index: 683

Text #1

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7057. Min Act: -0.0000

Data Index: 1823140 (The Pile)

Max Activating Token Index: 357

Text #2

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6815. Min Act: -0.0000

Data Index: 844593 (The Pile)

Max Activating Token Index: 638

Text #3

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7050. Min Act: -0.0000

Data Index: 471446 (The Pile)

Max Activating Token Index: 322

Text #4

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1482597 (The Pile)

Max Activating Token Index: 374

Text #5

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6174. Min Act: -0.0000

Data Index: 17063 (The Pile)

Max Activating Token Index: 429

Text #6

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6031. Min Act: -0.0000

Data Index: 763783 (The Pile)

Max Activating Token Index: 225

Text #7

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1520733 (The Pile)

Max Activating Token Index: 569

Text #8

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5910. Min Act: -0.0000

Data Index: 736929 (The Pile)

Max Activating Token Index: 212

Text #9

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6087. Min Act: -0.0000

Data Index: 1289057 (The Pile)

Max Activating Token Index: 936

Text #10

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1048676 (The Pile)

Max Activating Token Index: 728

Text #11

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5854. Min Act: -0.0000

Data Index: 175506 (The Pile)

Max Activating Token Index: 148

Text #12

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5790. Min Act: -0.0000

Data Index: 1872501 (The Pile)

Max Activating Token Index: 713

Text #13

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5751. Min Act: -0.0000

Data Index: 473538 (The Pile)

Max Activating Token Index: 475

Text #14

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5765. Min Act: -0.0000

Data Index: 1781896 (The Pile)

Max Activating Token Index: 739

Text #15

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5734. Min Act: -0.0000

Data Index: 708848 (The Pile)

Max Activating Token Index: 81

Text #16

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6077. Min Act: -0.0000

Data Index: 1196218 (The Pile)

Max Activating Token Index: 986

Text #17

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5886. Min Act: -0.0000

Data Index: 714749 (The Pile)

Max Activating Token Index: 203

Text #18

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5798. Min Act: -0.0000

Data Index: 1961729 (The Pile)

Max Activating Token Index: 182

Text #19

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6033. Min Act: -0.0000

Data Index: 53463 (The Pile)

Max Activating Token Index: 317