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

Dataset: The Pile

Neuron 1061 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: 1.9078. Min Range: -1.9078

Max Act: 1.9078. Min Act: -0.0000

Data Index: 1232335 (The Pile)

Max Activating Token Index: 980

Text #1

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.5226. Min Act: -0.0000

Data Index: 1538001 (The Pile)

Max Activating Token Index: 692

Text #2

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.4515. Min Act: -0.0000

Data Index: 1287349 (The Pile)

Max Activating Token Index: 889

Text #3

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.5078. Min Act: -0.0000

Data Index: 1557641 (The Pile)

Max Activating Token Index: 774

Text #4

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.4214. Min Act: -0.0000

Data Index: 97897 (The Pile)

Max Activating Token Index: 673

Text #5

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.2668. Min Act: -0.0000

Data Index: 386717 (The Pile)

Max Activating Token Index: 219

Text #6

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.1450. Min Act: -0.0000

Data Index: 1131568 (The Pile)

Max Activating Token Index: 979

Text #7

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.2215. Min Act: -0.0000

Data Index: 118283 (The Pile)

Max Activating Token Index: 475

Text #8

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.4449. Min Act: -0.0000

Data Index: 1283424 (The Pile)

Max Activating Token Index: 669

Text #9

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.2475. Min Act: -0.0000

Data Index: 965853 (The Pile)

Max Activating Token Index: 468

Text #10

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.3482. Min Act: -0.0000

Data Index: 1051765 (The Pile)

Max Activating Token Index: 798

Text #11

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.1597. Min Act: -0.0000

Data Index: 1888918 (The Pile)

Max Activating Token Index: 105

Text #12

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.1772. Min Act: -0.0000

Data Index: 1661976 (The Pile)

Max Activating Token Index: 76

Text #13

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.2468. Min Act: -0.0000

Data Index: 670393 (The Pile)

Max Activating Token Index: 298

Text #14

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.2097. Min Act: -0.0000

Data Index: 483272 (The Pile)

Max Activating Token Index: 450

Text #15

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.2400. Min Act: -0.0000

Data Index: 1377595 (The Pile)

Max Activating Token Index: 157

Text #16

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.2781. Min Act: -0.0000

Data Index: 539020 (The Pile)

Max Activating Token Index: 223

Text #17

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.1844. Min Act: -0.0000

Data Index: 1992420 (The Pile)

Max Activating Token Index: 227

Text #18

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.1836. Min Act: -0.0000

Data Index: 1455738 (The Pile)

Max Activating Token Index: 459

Text #19

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.1561. Min Act: -0.0000

Data Index: 1499445 (The Pile)

Max Activating Token Index: 824