Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1010 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1015. Min Range: -1.1015

Max Act: 1.0590. Min Act: -0.0000

Data Index: 1873912 (The Pile)

Max Activating Token Index: 488

Text #1

Max Range: 1.1015. Min Range: -1.1015

Max Act: 1.0862. Min Act: -0.0000

Data Index: 1341981 (The Pile)

Max Activating Token Index: 887

Text #2

Max Range: 1.1015. Min Range: -1.1015

Max Act: 1.0635. Min Act: -0.0000

Data Index: 229945 (The Pile)

Max Activating Token Index: 1010

Text #3

Max Range: 1.1015. Min Range: -1.1015

Max Act: 1.1015. Min Act: -0.0000

Data Index: 1797192 (The Pile)

Max Activating Token Index: 734

Text #4

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8140. Min Act: -0.0000

Data Index: 1183252 (The Pile)

Max Activating Token Index: 92

Text #5

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.9266. Min Act: -0.0000

Data Index: 267140 (The Pile)

Max Activating Token Index: 587

Text #6

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.9060. Min Act: -0.0000

Data Index: 1654217 (The Pile)

Max Activating Token Index: 438

Text #7

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8912. Min Act: -0.0000

Data Index: 1522586 (The Pile)

Max Activating Token Index: 775

Text #8

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.9442. Min Act: -0.0000

Data Index: 702143 (The Pile)

Max Activating Token Index: 557

Text #9

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.9571. Min Act: -0.0000

Data Index: 1918361 (The Pile)

Max Activating Token Index: 18

Text #10

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8506. Min Act: -0.0000

Data Index: 1244919 (The Pile)

Max Activating Token Index: 352

Text #11

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1456371 (The Pile)

Max Activating Token Index: 861

Text #12

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.9786. Min Act: -0.0000

Data Index: 644453 (The Pile)

Max Activating Token Index: 638

Text #13

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8928. Min Act: -0.0000

Data Index: 1796456 (The Pile)

Max Activating Token Index: 211

Text #14

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.7028. Min Act: -0.0000

Data Index: 1606716 (The Pile)

Max Activating Token Index: 693

Text #15

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8267. Min Act: -0.0000

Data Index: 798612 (The Pile)

Max Activating Token Index: 758

Text #16

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8619. Min Act: -0.0000

Data Index: 1301331 (The Pile)

Max Activating Token Index: 738

Text #17

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8537. Min Act: -0.0000

Data Index: 1355378 (The Pile)

Max Activating Token Index: 124

Text #18

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.9218. Min Act: -0.0000

Data Index: 1559531 (The Pile)

Max Activating Token Index: 628

Text #19

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8078. Min Act: -0.0000

Data Index: 1997141 (The Pile)

Max Activating Token Index: 219