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

Dataset: The Pile

Neuron 2648 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.9750. Min Act: -0.0000

Data Index: 1042682 (The Pile)

Max Activating Token Index: 281

Text #1

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.9092. Min Act: -0.0000

Data Index: 1927077 (The Pile)

Max Activating Token Index: 493

Text #2

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.8275. Min Act: -0.0000

Data Index: 1212690 (The Pile)

Max Activating Token Index: 543

Text #3

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.6868. Min Act: -0.0000

Data Index: 42342 (The Pile)

Max Activating Token Index: 177

Text #4

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.5854. Min Act: -0.0000

Data Index: 179612 (The Pile)

Max Activating Token Index: 897

Text #5

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.5753. Min Act: -0.0000

Data Index: 1231615 (The Pile)

Max Activating Token Index: 217

Text #6

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.5956. Min Act: -0.0000

Data Index: 630242 (The Pile)

Max Activating Token Index: 833

Text #7

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1521898 (The Pile)

Max Activating Token Index: 475

Text #8

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.5868. Min Act: -0.0000

Data Index: 922335 (The Pile)

Max Activating Token Index: 173

Text #9

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.5862. Min Act: -0.0000

Data Index: 120334 (The Pile)

Max Activating Token Index: 148

Text #10

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1297222 (The Pile)

Max Activating Token Index: 951

Text #11

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.5097. Min Act: -0.0000

Data Index: 190595 (The Pile)

Max Activating Token Index: 632

Text #12

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.5732. Min Act: -0.0000

Data Index: 1633548 (The Pile)

Max Activating Token Index: 139

Text #13

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.5795. Min Act: -0.0000

Data Index: 1727652 (The Pile)

Max Activating Token Index: 718

Text #14

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.5725. Min Act: -0.0000

Data Index: 183637 (The Pile)

Max Activating Token Index: 993

Text #15

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1366211 (The Pile)

Max Activating Token Index: 841

Text #16

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.6381. Min Act: -0.0000

Data Index: 1391417 (The Pile)

Max Activating Token Index: 671

Text #17

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.5534. Min Act: -0.0000

Data Index: 524896 (The Pile)

Max Activating Token Index: 658

Text #18

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.5654. Min Act: -0.0000

Data Index: 680817 (The Pile)

Max Activating Token Index: 741

Text #19

Max Range: 0.9750. Min Range: -0.9750

Max Act: 0.5397. Min Act: -0.0000

Data Index: 174882 (The Pile)

Max Activating Token Index: 1004