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

Dataset: The Pile

Neuron 1785 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.9867. Min Act: -0.0000

Data Index: 621123 (The Pile)

Max Activating Token Index: 743

Text #1

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8901. Min Act: -0.0000

Data Index: 1088125 (The Pile)

Max Activating Token Index: 1014

Text #2

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.9601. Min Act: -0.0000

Data Index: 1570933 (The Pile)

Max Activating Token Index: 909

Text #3

Max Range: 1.0151. Min Range: -1.0151

Max Act: 1.0151. Min Act: -0.0000

Data Index: 632672 (The Pile)

Max Activating Token Index: 785

Text #4

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.9122. Min Act: -0.0000

Data Index: 1918025 (The Pile)

Max Activating Token Index: 517

Text #5

Max Range: 1.0151. Min Range: -1.0151

Max Act: 1.0135. Min Act: -0.0000

Data Index: 912061 (The Pile)

Max Activating Token Index: 645

Text #6

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.9055. Min Act: -0.0000

Data Index: 1900903 (The Pile)

Max Activating Token Index: 802

Text #7

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.9089. Min Act: -0.0000

Data Index: 1074156 (The Pile)

Max Activating Token Index: 674

Text #8

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8724. Min Act: -0.0000

Data Index: 739659 (The Pile)

Max Activating Token Index: 316

Text #9

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8563. Min Act: -0.0000

Data Index: 1378099 (The Pile)

Max Activating Token Index: 360

Text #10

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7875. Min Act: -0.0000

Data Index: 220264 (The Pile)

Max Activating Token Index: 548

Text #11

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8307. Min Act: -0.0000

Data Index: 783538 (The Pile)

Max Activating Token Index: 462

Text #12

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1643225 (The Pile)

Max Activating Token Index: 998

Text #13

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8640. Min Act: -0.0000

Data Index: 1282244 (The Pile)

Max Activating Token Index: 439

Text #14

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8652. Min Act: -0.0000

Data Index: 533464 (The Pile)

Max Activating Token Index: 166

Text #15

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8521. Min Act: -0.0000

Data Index: 1271116 (The Pile)

Max Activating Token Index: 440

Text #16

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7774. Min Act: -0.0000

Data Index: 1812803 (The Pile)

Max Activating Token Index: 621

Text #17

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8259. Min Act: -0.0000

Data Index: 655901 (The Pile)

Max Activating Token Index: 163

Text #18

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8307. Min Act: -0.0000

Data Index: 476745 (The Pile)

Max Activating Token Index: 628

Text #19

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7184. Min Act: -0.0000

Data Index: 1944708 (The Pile)

Max Activating Token Index: 436