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

Dataset: The Pile

Neuron 3816 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: 1.4850. Min Range: -1.4850

Max Act: 1.4850. Min Act: -0.0000

Data Index: 1400400 (The Pile)

Max Activating Token Index: 66

Text #1

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.3598. Min Act: -0.0000

Data Index: 1331875 (The Pile)

Max Activating Token Index: 93

Text #2

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.2530. Min Act: -0.0000

Data Index: 827030 (The Pile)

Max Activating Token Index: 327

Text #3

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.3217. Min Act: -0.0000

Data Index: 1546904 (The Pile)

Max Activating Token Index: 989

Text #4

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.3076. Min Act: -0.0000

Data Index: 354031 (The Pile)

Max Activating Token Index: 597

Text #5

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.2873. Min Act: -0.0000

Data Index: 517384 (The Pile)

Max Activating Token Index: 921

Text #6

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.3557. Min Act: -0.0000

Data Index: 1096646 (The Pile)

Max Activating Token Index: 517

Text #7

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.2675. Min Act: -0.0000

Data Index: 1314762 (The Pile)

Max Activating Token Index: 314

Text #8

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.2715. Min Act: -0.0000

Data Index: 1335146 (The Pile)

Max Activating Token Index: 723

Text #9

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.2610. Min Act: -0.0000

Data Index: 1873589 (The Pile)

Max Activating Token Index: 230

Text #10

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.2435. Min Act: -0.0000

Data Index: 688692 (The Pile)

Max Activating Token Index: 627

Text #11

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.1761. Min Act: -0.0000

Data Index: 1866136 (The Pile)

Max Activating Token Index: 93

Text #12

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.1738. Min Act: -0.0000

Data Index: 682292 (The Pile)

Max Activating Token Index: 231

Text #13

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.1083. Min Act: -0.0000

Data Index: 709067 (The Pile)

Max Activating Token Index: 28

Text #14

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.1694. Min Act: -0.0000

Data Index: 836617 (The Pile)

Max Activating Token Index: 286

Text #15

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.1722. Min Act: -0.0000

Data Index: 455104 (The Pile)

Max Activating Token Index: 217

Text #16

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.2378. Min Act: -0.0000

Data Index: 1755850 (The Pile)

Max Activating Token Index: 418

Text #17

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.2329. Min Act: -0.0000

Data Index: 851796 (The Pile)

Max Activating Token Index: 598

Text #18

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.2320. Min Act: -0.0000

Data Index: 1070187 (The Pile)

Max Activating Token Index: 434

Text #19

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.3110. Min Act: -0.0000

Data Index: 662359 (The Pile)

Max Activating Token Index: 540