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

Dataset: The Pile

Neuron 1357 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.2643. Min Act: -0.0000

Data Index: 1135877 (The Pile)

Max Activating Token Index: 275

Text #1

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.2766. Min Act: -0.0000

Data Index: 368836 (The Pile)

Max Activating Token Index: 335

Text #2

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1885. Min Act: -0.0000

Data Index: 1282082 (The Pile)

Max Activating Token Index: 269

Text #3

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1226. Min Act: -0.0000

Data Index: 1688205 (The Pile)

Max Activating Token Index: 803

Text #4

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0663. Min Act: -0.0000

Data Index: 144222 (The Pile)

Max Activating Token Index: 110

Text #5

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0969. Min Act: -0.0000

Data Index: 1569913 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0436. Min Act: -0.0000

Data Index: 1259774 (The Pile)

Max Activating Token Index: 784

Text #7

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.2066. Min Act: -0.0000

Data Index: 1827340 (The Pile)

Max Activating Token Index: 818

Text #8

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0539. Min Act: -0.0000

Data Index: 117191 (The Pile)

Max Activating Token Index: 567

Text #9

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0138. Min Act: -0.0000

Data Index: 1237333 (The Pile)

Max Activating Token Index: 381

Text #10

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1725. Min Act: -0.0000

Data Index: 669097 (The Pile)

Max Activating Token Index: 827

Text #11

Max Range: 1.2766. Min Range: -1.2766

Max Act: 0.9872. Min Act: -0.0000

Data Index: 223022 (The Pile)

Max Activating Token Index: 573

Text #12

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0264. Min Act: -0.0000

Data Index: 754580 (The Pile)

Max Activating Token Index: 232

Text #13

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0058. Min Act: -0.0000

Data Index: 1158434 (The Pile)

Max Activating Token Index: 432

Text #14

Max Range: 1.2766. Min Range: -1.2766

Max Act: 0.9634. Min Act: -0.0000

Data Index: 928733 (The Pile)

Max Activating Token Index: 784

Text #15

Max Range: 1.2766. Min Range: -1.2766

Max Act: 0.9788. Min Act: -0.0000

Data Index: 463353 (The Pile)

Max Activating Token Index: 147

Text #16

Max Range: 1.2766. Min Range: -1.2766

Max Act: 0.9813. Min Act: -0.0000

Data Index: 1751990 (The Pile)

Max Activating Token Index: 682

Text #17

Max Range: 1.2766. Min Range: -1.2766

Max Act: 0.9993. Min Act: -0.0000

Data Index: 1192445 (The Pile)

Max Activating Token Index: 618

Text #18

Max Range: 1.2766. Min Range: -1.2766

Max Act: 0.9187. Min Act: -0.0000

Data Index: 567833 (The Pile)

Max Activating Token Index: 418

Text #19

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0052. Min Act: -0.0000

Data Index: 259834 (The Pile)

Max Activating Token Index: 496