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

Dataset: The Pile

Neuron 2184 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.4105. Min Act: -0.0000

Data Index: 1199637 (The Pile)

Max Activating Token Index: 684

Text #1

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.3392. Min Act: -0.0000

Data Index: 289633 (The Pile)

Max Activating Token Index: 175

Text #2

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.3066. Min Act: -0.0000

Data Index: 1264404 (The Pile)

Max Activating Token Index: 942

Text #3

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2965. Min Act: -0.0000

Data Index: 727927 (The Pile)

Max Activating Token Index: 90

Text #4

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2972. Min Act: -0.0000

Data Index: 1049966 (The Pile)

Max Activating Token Index: 177

Text #5

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2996. Min Act: -0.0000

Data Index: 1465211 (The Pile)

Max Activating Token Index: 277

Text #6

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2986. Min Act: -0.0000

Data Index: 1144646 (The Pile)

Max Activating Token Index: 429

Text #7

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2893. Min Act: -0.0000

Data Index: 1426555 (The Pile)

Max Activating Token Index: 146

Text #8

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2505. Min Act: -0.0000

Data Index: 1424446 (The Pile)

Max Activating Token Index: 764

Text #9

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2791. Min Act: -0.0000

Data Index: 1751223 (The Pile)

Max Activating Token Index: 557

Text #10

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2894. Min Act: -0.0000

Data Index: 1815937 (The Pile)

Max Activating Token Index: 241

Text #11

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2668. Min Act: -0.0000

Data Index: 755636 (The Pile)

Max Activating Token Index: 138

Text #12

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2678. Min Act: -0.0000

Data Index: 282888 (The Pile)

Max Activating Token Index: 103

Text #13

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2666. Min Act: -0.0000

Data Index: 1511746 (The Pile)

Max Activating Token Index: 451

Text #14

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2653. Min Act: -0.0000

Data Index: 118568 (The Pile)

Max Activating Token Index: 491

Text #15

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1746943 (The Pile)

Max Activating Token Index: 781

Text #16

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2471. Min Act: -0.0000

Data Index: 1756442 (The Pile)

Max Activating Token Index: 887

Text #17

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1108138 (The Pile)

Max Activating Token Index: 370

Text #18

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2281. Min Act: -0.0000

Data Index: 1680731 (The Pile)

Max Activating Token Index: 769

Text #19

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2474. Min Act: -0.0000

Data Index: 385015 (The Pile)

Max Activating Token Index: 55