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

Dataset: The Pile

Neuron 1002 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: 1.4504. Min Range: -1.4504

Max Act: 1.4504. Min Act: -0.0000

Data Index: 471498 (The Pile)

Max Activating Token Index: 309

Text #1

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.1828. Min Act: -0.0000

Data Index: 316040 (The Pile)

Max Activating Token Index: 479

Text #2

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.0901. Min Act: -0.0000

Data Index: 1933412 (The Pile)

Max Activating Token Index: 89

Text #3

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.1087. Min Act: -0.0000

Data Index: 993851 (The Pile)

Max Activating Token Index: 81

Text #4

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.3352. Min Act: -0.0000

Data Index: 1136310 (The Pile)

Max Activating Token Index: 67

Text #5

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.0913. Min Act: -0.0000

Data Index: 753203 (The Pile)

Max Activating Token Index: 354

Text #6

Max Range: 1.4504. Min Range: -1.4504

Max Act: 0.8847. Min Act: -0.0000

Data Index: 653075 (The Pile)

Max Activating Token Index: 286

Text #7

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.0584. Min Act: -0.0000

Data Index: 735471 (The Pile)

Max Activating Token Index: 192

Text #8

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.0567. Min Act: -0.0000

Data Index: 1753430 (The Pile)

Max Activating Token Index: 237

Text #9

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.0402. Min Act: -0.0000

Data Index: 1521920 (The Pile)

Max Activating Token Index: 276

Text #10

Max Range: 1.4504. Min Range: -1.4504

Max Act: 0.9818. Min Act: -0.0000

Data Index: 1029582 (The Pile)

Max Activating Token Index: 482

Text #11

Max Range: 1.4504. Min Range: -1.4504

Max Act: 0.9818. Min Act: -0.0000

Data Index: 70809 (The Pile)

Max Activating Token Index: 674

Text #12

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.0406. Min Act: -0.0000

Data Index: 524379 (The Pile)

Max Activating Token Index: 171

Text #13

Max Range: 1.4504. Min Range: -1.4504

Max Act: 0.9049. Min Act: -0.0000

Data Index: 862873 (The Pile)

Max Activating Token Index: 802

Text #14

Max Range: 1.4504. Min Range: -1.4504

Max Act: 0.9149. Min Act: -0.0000

Data Index: 1477016 (The Pile)

Max Activating Token Index: 214

Text #15

Max Range: 1.4504. Min Range: -1.4504

Max Act: 0.9873. Min Act: -0.0000

Data Index: 1425182 (The Pile)

Max Activating Token Index: 578

Text #16

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.0650. Min Act: -0.0000

Data Index: 1804169 (The Pile)

Max Activating Token Index: 808

Text #17

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.0706. Min Act: -0.0000

Data Index: 1655152 (The Pile)

Max Activating Token Index: 208

Text #18

Max Range: 1.4504. Min Range: -1.4504

Max Act: 0.8668. Min Act: -0.0000

Data Index: 1838845 (The Pile)

Max Activating Token Index: 237

Text #19

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.0032. Min Act: -0.0000

Data Index: 884696 (The Pile)

Max Activating Token Index: 172