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

Dataset: The Pile

Neuron 2025 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: 0.7988. Min Range: -0.7988

Max Act: 0.7988. Min Act: -0.0000

Data Index: 1510509 (The Pile)

Max Activating Token Index: 487

Text #1

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.7067. Min Act: -0.0000

Data Index: 399140 (The Pile)

Max Activating Token Index: 1018

Text #2

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6724. Min Act: -0.0000

Data Index: 1103005 (The Pile)

Max Activating Token Index: 514

Text #3

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5695. Min Act: -0.0000

Data Index: 1742771 (The Pile)

Max Activating Token Index: 215

Text #4

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6307. Min Act: -0.0000

Data Index: 1046144 (The Pile)

Max Activating Token Index: 398

Text #5

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6488. Min Act: -0.0000

Data Index: 1324809 (The Pile)

Max Activating Token Index: 586

Text #6

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6064. Min Act: -0.0000

Data Index: 1047462 (The Pile)

Max Activating Token Index: 504

Text #7

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6653. Min Act: -0.0000

Data Index: 1700243 (The Pile)

Max Activating Token Index: 499

Text #8

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5906. Min Act: -0.0000

Data Index: 820393 (The Pile)

Max Activating Token Index: 397

Text #9

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1142579 (The Pile)

Max Activating Token Index: 641

Text #10

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6055. Min Act: -0.0000

Data Index: 954823 (The Pile)

Max Activating Token Index: 713

Text #11

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1245548 (The Pile)

Max Activating Token Index: 438

Text #12

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5471. Min Act: -0.0000

Data Index: 1138063 (The Pile)

Max Activating Token Index: 68

Text #13

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5965. Min Act: -0.0000

Data Index: 86241 (The Pile)

Max Activating Token Index: 840

Text #14

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6244. Min Act: -0.0000

Data Index: 1490464 (The Pile)

Max Activating Token Index: 1008

Text #15

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5734. Min Act: -0.0000

Data Index: 719011 (The Pile)

Max Activating Token Index: 1009

Text #16

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6036. Min Act: -0.0000

Data Index: 1006606 (The Pile)

Max Activating Token Index: 948

Text #17

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6068. Min Act: -0.0000

Data Index: 212862 (The Pile)

Max Activating Token Index: 786

Text #18

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5255. Min Act: -0.0000

Data Index: 242658 (The Pile)

Max Activating Token Index: 673

Text #19

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5760. Min Act: -0.0000

Data Index: 659464 (The Pile)

Max Activating Token Index: 995