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

Dataset: The Pile

Neuron 2255 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: 1.1109. Min Range: -1.1109

Max Act: 1.0246. Min Act: -0.0000

Data Index: 152797 (The Pile)

Max Activating Token Index: 967

Text #1

Max Range: 1.1109. Min Range: -1.1109

Max Act: 1.1109. Min Act: -0.0000

Data Index: 1549585 (The Pile)

Max Activating Token Index: 62

Text #2

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.9597. Min Act: -0.0000

Data Index: 1789479 (The Pile)

Max Activating Token Index: 499

Text #3

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.9325. Min Act: -0.0000

Data Index: 1234929 (The Pile)

Max Activating Token Index: 854

Text #4

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.9488. Min Act: -0.0000

Data Index: 794561 (The Pile)

Max Activating Token Index: 477

Text #5

Max Range: 1.1109. Min Range: -1.1109

Max Act: 1.0453. Min Act: -0.0000

Data Index: 423872 (The Pile)

Max Activating Token Index: 665

Text #6

Max Range: 1.1109. Min Range: -1.1109

Max Act: 1.0060. Min Act: -0.0000

Data Index: 770651 (The Pile)

Max Activating Token Index: 268

Text #7

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.9882. Min Act: -0.0000

Data Index: 1811935 (The Pile)

Max Activating Token Index: 187

Text #8

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8934. Min Act: -0.0000

Data Index: 986882 (The Pile)

Max Activating Token Index: 125

Text #9

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8923. Min Act: -0.0000

Data Index: 1055246 (The Pile)

Max Activating Token Index: 1004

Text #10

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.9243. Min Act: -0.0000

Data Index: 1088695 (The Pile)

Max Activating Token Index: 842

Text #11

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.9074. Min Act: -0.0000

Data Index: 1094526 (The Pile)

Max Activating Token Index: 758

Text #12

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.9681. Min Act: -0.0000

Data Index: 1061530 (The Pile)

Max Activating Token Index: 41

Text #13

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8272. Min Act: -0.0000

Data Index: 1451961 (The Pile)

Max Activating Token Index: 631

Text #14

Max Range: 1.1109. Min Range: -1.1109

Max Act: 1.0396. Min Act: -0.0000

Data Index: 1383694 (The Pile)

Max Activating Token Index: 778

Text #15

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8994. Min Act: -0.0000

Data Index: 1563769 (The Pile)

Max Activating Token Index: 744

Text #16

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.9110. Min Act: -0.0000

Data Index: 1336567 (The Pile)

Max Activating Token Index: 886

Text #17

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.9086. Min Act: -0.0000

Data Index: 1816574 (The Pile)

Max Activating Token Index: 312

Text #18

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.9497. Min Act: -0.0000

Data Index: 262714 (The Pile)

Max Activating Token Index: 495

Text #19

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8841. Min Act: -0.0000

Data Index: 1879712 (The Pile)

Max Activating Token Index: 429