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

Dataset: The Pile

Neuron 4416 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: 0.8954. Min Range: -0.8954

Max Act: 0.8954. Min Act: -0.0000

Data Index: 1342659 (The Pile)

Max Activating Token Index: 571

Text #1

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.8949. Min Act: -0.0000

Data Index: 1867951 (The Pile)

Max Activating Token Index: 46

Text #2

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.8634. Min Act: -0.0000

Data Index: 999340 (The Pile)

Max Activating Token Index: 55

Text #3

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.8383. Min Act: -0.0000

Data Index: 9774 (The Pile)

Max Activating Token Index: 258

Text #4

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.7796. Min Act: -0.0000

Data Index: 917075 (The Pile)

Max Activating Token Index: 145

Text #5

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.8724. Min Act: -0.0000

Data Index: 227240 (The Pile)

Max Activating Token Index: 44

Text #6

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.8449. Min Act: -0.0000

Data Index: 685194 (The Pile)

Max Activating Token Index: 513

Text #7

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.8313. Min Act: -0.0000

Data Index: 1150615 (The Pile)

Max Activating Token Index: 551

Text #8

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.8339. Min Act: -0.0000

Data Index: 1199650 (The Pile)

Max Activating Token Index: 149

Text #9

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.8057. Min Act: -0.0000

Data Index: 406963 (The Pile)

Max Activating Token Index: 657

Text #10

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.7945. Min Act: -0.0000

Data Index: 1805583 (The Pile)

Max Activating Token Index: 289

Text #11

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.7706. Min Act: -0.0000

Data Index: 381657 (The Pile)

Max Activating Token Index: 274

Text #12

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.7446. Min Act: -0.0000

Data Index: 1076868 (The Pile)

Max Activating Token Index: 837

Text #13

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.7613. Min Act: -0.0000

Data Index: 1060584 (The Pile)

Max Activating Token Index: 521

Text #14

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.7408. Min Act: -0.0000

Data Index: 885997 (The Pile)

Max Activating Token Index: 48

Text #15

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.8337. Min Act: -0.0000

Data Index: 1503030 (The Pile)

Max Activating Token Index: 483

Text #16

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.7836. Min Act: -0.0000

Data Index: 273320 (The Pile)

Max Activating Token Index: 482

Text #17

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.8114. Min Act: -0.0000

Data Index: 1955664 (The Pile)

Max Activating Token Index: 574

Text #18

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.8055. Min Act: -0.0000

Data Index: 702236 (The Pile)

Max Activating Token Index: 126

Text #19

Max Range: 0.8954. Min Range: -0.8954

Max Act: 0.7790. Min Act: -0.0000

Data Index: 432479 (The Pile)

Max Activating Token Index: 414