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

Dataset: The Pile

Neuron 2988 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.7915. Min Act: -0.0000

Data Index: 1600287 (The Pile)

Max Activating Token Index: 444

Text #1

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.8435. Min Act: -0.0000

Data Index: 226582 (The Pile)

Max Activating Token Index: 382

Text #2

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.7207. Min Act: -0.0000

Data Index: 957589 (The Pile)

Max Activating Token Index: 855

Text #3

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.7707. Min Act: -0.0000

Data Index: 1097264 (The Pile)

Max Activating Token Index: 688

Text #4

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.7613. Min Act: -0.0000

Data Index: 341689 (The Pile)

Max Activating Token Index: 130

Text #5

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.7469. Min Act: -0.0000

Data Index: 1942511 (The Pile)

Max Activating Token Index: 176

Text #6

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.7411. Min Act: -0.0000

Data Index: 515925 (The Pile)

Max Activating Token Index: 174

Text #7

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.7707. Min Act: -0.0000

Data Index: 1490738 (The Pile)

Max Activating Token Index: 87

Text #8

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.6835. Min Act: -0.0000

Data Index: 1358673 (The Pile)

Max Activating Token Index: 204

Text #9

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.7285. Min Act: -0.0000

Data Index: 321063 (The Pile)

Max Activating Token Index: 254

Text #10

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.6750. Min Act: -0.0000

Data Index: 469612 (The Pile)

Max Activating Token Index: 343

Text #11

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.6550. Min Act: -0.0000

Data Index: 1303424 (The Pile)

Max Activating Token Index: 188

Text #12

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.6991. Min Act: -0.0000

Data Index: 1833615 (The Pile)

Max Activating Token Index: 590

Text #13

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.6797. Min Act: -0.0000

Data Index: 1764674 (The Pile)

Max Activating Token Index: 664

Text #14

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.7375. Min Act: -0.0000

Data Index: 596421 (The Pile)

Max Activating Token Index: 305

Text #15

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.6672. Min Act: -0.0000

Data Index: 1652227 (The Pile)

Max Activating Token Index: 273

Text #16

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.6848. Min Act: -0.0000

Data Index: 689415 (The Pile)

Max Activating Token Index: 782

Text #17

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.6641. Min Act: -0.0000

Data Index: 330659 (The Pile)

Max Activating Token Index: 286

Text #18

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.6935. Min Act: -0.0000

Data Index: 306313 (The Pile)

Max Activating Token Index: 990

Text #19

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.6749. Min Act: -0.0000

Data Index: 927128 (The Pile)

Max Activating Token Index: 345