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

Dataset: The Pile

Neuron 5081 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: 0.8311. Min Range: -0.8311

Max Act: 0.8125. Min Act: -0.0000

Data Index: 1882432 (The Pile)

Max Activating Token Index: 335

Text #1

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.8311. Min Act: -0.0000

Data Index: 948804 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7859. Min Act: -0.0000

Data Index: 1094623 (The Pile)

Max Activating Token Index: 312

Text #3

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7045. Min Act: -0.0000

Data Index: 92521 (The Pile)

Max Activating Token Index: 619

Text #4

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6303. Min Act: -0.0000

Data Index: 1741173 (The Pile)

Max Activating Token Index: 949

Text #5

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6940. Min Act: -0.0000

Data Index: 1738287 (The Pile)

Max Activating Token Index: 301

Text #6

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6120. Min Act: -0.0000

Data Index: 70750 (The Pile)

Max Activating Token Index: 107

Text #7

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7299. Min Act: -0.0000

Data Index: 1742471 (The Pile)

Max Activating Token Index: 201

Text #8

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6685. Min Act: -0.0000

Data Index: 872092 (The Pile)

Max Activating Token Index: 245

Text #9

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6757. Min Act: -0.0000

Data Index: 1757789 (The Pile)

Max Activating Token Index: 912

Text #10

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6712. Min Act: -0.0000

Data Index: 1472951 (The Pile)

Max Activating Token Index: 201

Text #11

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6294. Min Act: -0.0000

Data Index: 517730 (The Pile)

Max Activating Token Index: 583

Text #12

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6222. Min Act: -0.0000

Data Index: 999547 (The Pile)

Max Activating Token Index: 390

Text #13

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7042. Min Act: -0.0000

Data Index: 1116191 (The Pile)

Max Activating Token Index: 339

Text #14

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6361. Min Act: -0.0000

Data Index: 1029155 (The Pile)

Max Activating Token Index: 405

Text #15

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6665. Min Act: -0.0000

Data Index: 1108640 (The Pile)

Max Activating Token Index: 119

Text #16

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6914. Min Act: -0.0000

Data Index: 1688573 (The Pile)

Max Activating Token Index: 420

Text #17

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6287. Min Act: -0.0000

Data Index: 501118 (The Pile)

Max Activating Token Index: 408

Text #18

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6928. Min Act: -0.0000

Data Index: 1680785 (The Pile)

Max Activating Token Index: 109

Text #19

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1123175 (The Pile)

Max Activating Token Index: 545