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

Dataset: The Pile

Neuron 2482 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: 1.6677. Min Range: -1.6677

Max Act: 1.6677. Min Act: -0.0000

Data Index: 1742758 (The Pile)

Max Activating Token Index: 336

Text #1

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.6492. Min Act: -0.0000

Data Index: 1817747 (The Pile)

Max Activating Token Index: 198

Text #2

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.4169. Min Act: -0.0000

Data Index: 1643744 (The Pile)

Max Activating Token Index: 512

Text #3

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.3507. Min Act: -0.0001

Data Index: 1152248 (The Pile)

Max Activating Token Index: 485

Text #4

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.3737. Min Act: -0.0000

Data Index: 128598 (The Pile)

Max Activating Token Index: 177

Text #5

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.5142. Min Act: -0.0000

Data Index: 654654 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.3810. Min Act: -0.0000

Data Index: 1608681 (The Pile)

Max Activating Token Index: 779

Text #7

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.3584. Min Act: -0.0000

Data Index: 1609696 (The Pile)

Max Activating Token Index: 462

Text #8

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.3530. Min Act: -0.0000

Data Index: 1308452 (The Pile)

Max Activating Token Index: 630

Text #9

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.4999. Min Act: -0.0000

Data Index: 988752 (The Pile)

Max Activating Token Index: 718

Text #10

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.1908. Min Act: -0.0000

Data Index: 189701 (The Pile)

Max Activating Token Index: 745

Text #11

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.2770. Min Act: -0.0000

Data Index: 1982052 (The Pile)

Max Activating Token Index: 125

Text #12

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.3316. Min Act: -0.0001

Data Index: 522551 (The Pile)

Max Activating Token Index: 366

Text #13

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.4229. Min Act: -0.0000

Data Index: 1284396 (The Pile)

Max Activating Token Index: 182

Text #14

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.4648. Min Act: -0.0000

Data Index: 481448 (The Pile)

Max Activating Token Index: 278

Text #15

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.4347. Min Act: -0.0000

Data Index: 1238770 (The Pile)

Max Activating Token Index: 277

Text #16

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.2645. Min Act: -0.0000

Data Index: 1304170 (The Pile)

Max Activating Token Index: 868

Text #17

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.5509. Min Act: -0.0000

Data Index: 1622255 (The Pile)

Max Activating Token Index: 172

Text #18

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.3505. Min Act: -0.0000

Data Index: 1048606 (The Pile)

Max Activating Token Index: 853

Text #19

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.0418. Min Act: -0.0000

Data Index: 60764 (The Pile)

Max Activating Token Index: 631