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

Dataset: The Pile

Neuron 3595 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: 1.3161. Min Range: -1.3161

Max Act: 1.3161. Min Act: -0.0000

Data Index: 1845164 (The Pile)

Max Activating Token Index: 665

Text #1

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.2742. Min Act: -0.0000

Data Index: 1972843 (The Pile)

Max Activating Token Index: 373

Text #2

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.2446. Min Act: -0.0000

Data Index: 250922 (The Pile)

Max Activating Token Index: 387

Text #3

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.1558. Min Act: -0.0000

Data Index: 34305 (The Pile)

Max Activating Token Index: 145

Text #4

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.1380. Min Act: -0.0000

Data Index: 604664 (The Pile)

Max Activating Token Index: 712

Text #5

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.2123. Min Act: -0.0000

Data Index: 1196075 (The Pile)

Max Activating Token Index: 538

Text #6

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.2241. Min Act: -0.0000

Data Index: 1633733 (The Pile)

Max Activating Token Index: 292

Text #7

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.1610. Min Act: -0.0000

Data Index: 286392 (The Pile)

Max Activating Token Index: 648

Text #8

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.0958. Min Act: -0.0000

Data Index: 1446921 (The Pile)

Max Activating Token Index: 89

Text #9

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.2119. Min Act: -0.0000

Data Index: 1073926 (The Pile)

Max Activating Token Index: 167

Text #10

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.1912. Min Act: -0.0000

Data Index: 1479547 (The Pile)

Max Activating Token Index: 51

Text #11

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.2628. Min Act: -0.0000

Data Index: 658234 (The Pile)

Max Activating Token Index: 469

Text #12

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.0521. Min Act: -0.0000

Data Index: 1959096 (The Pile)

Max Activating Token Index: 163

Text #13

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.1595. Min Act: -0.0000

Data Index: 1949502 (The Pile)

Max Activating Token Index: 291

Text #14

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.1740. Min Act: -0.0000

Data Index: 1835655 (The Pile)

Max Activating Token Index: 318

Text #15

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.1646. Min Act: -0.0000

Data Index: 234520 (The Pile)

Max Activating Token Index: 952

Text #16

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.0960. Min Act: -0.0000

Data Index: 1245016 (The Pile)

Max Activating Token Index: 376

Text #17

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.1042. Min Act: -0.0000

Data Index: 1065684 (The Pile)

Max Activating Token Index: 487

Text #18

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.1681. Min Act: -0.0000

Data Index: 215197 (The Pile)

Max Activating Token Index: 599

Text #19

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.1071. Min Act: -0.0000

Data Index: 1611770 (The Pile)

Max Activating Token Index: 204