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

Dataset: The Pile

Neuron 3454 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: 0.1468. Min Range: -0.1468

Max Act: 0.1468. Min Act: -0.0000

Data Index: 1725499 (The Pile)

Max Activating Token Index: 679

Text #1

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1254. Min Act: -0.0000

Data Index: 376167 (The Pile)

Max Activating Token Index: 500

Text #2

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1728926 (The Pile)

Max Activating Token Index: 349

Text #3

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1052. Min Act: -0.0000

Data Index: 1643957 (The Pile)

Max Activating Token Index: 258

Text #4

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0980. Min Act: -0.0000

Data Index: 1280432 (The Pile)

Max Activating Token Index: 531

Text #5

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1011. Min Act: -0.0000

Data Index: 329063 (The Pile)

Max Activating Token Index: 113

Text #6

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0966. Min Act: -0.0000

Data Index: 1020573 (The Pile)

Max Activating Token Index: 69

Text #7

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0940. Min Act: -0.0000

Data Index: 1824458 (The Pile)

Max Activating Token Index: 302

Text #8

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0846. Min Act: -0.0000

Data Index: 747815 (The Pile)

Max Activating Token Index: 365

Text #9

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0803. Min Act: -0.0000

Data Index: 570487 (The Pile)

Max Activating Token Index: 154

Text #10

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0889. Min Act: -0.0000

Data Index: 294563 (The Pile)

Max Activating Token Index: 278

Text #11

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0826. Min Act: -0.0000

Data Index: 501256 (The Pile)

Max Activating Token Index: 409

Text #12

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0821. Min Act: -0.0000

Data Index: 630668 (The Pile)

Max Activating Token Index: 19

Text #13

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0845. Min Act: -0.0000

Data Index: 1417961 (The Pile)

Max Activating Token Index: 896

Text #14

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0775. Min Act: -0.0000

Data Index: 1656083 (The Pile)

Max Activating Token Index: 758

Text #15

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0877. Min Act: -0.0000

Data Index: 155216 (The Pile)

Max Activating Token Index: 127

Text #16

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0840. Min Act: -0.0000

Data Index: 1339637 (The Pile)

Max Activating Token Index: 221

Text #17

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0830. Min Act: -0.0000

Data Index: 1710167 (The Pile)

Max Activating Token Index: 482

Text #18

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0826. Min Act: -0.0000

Data Index: 342468 (The Pile)

Max Activating Token Index: 141

Text #19

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0798. Min Act: -0.0000

Data Index: 905830 (The Pile)

Max Activating Token Index: 674