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

Dataset: The Pile

Neuron 1219 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: 1.0670. Min Range: -1.0670

Max Act: 1.0633. Min Act: -0.0000

Data Index: 1728632 (The Pile)

Max Activating Token Index: 360

Text #1

Max Range: 1.0670. Min Range: -1.0670

Max Act: 1.0670. Min Act: -0.0000

Data Index: 217889 (The Pile)

Max Activating Token Index: 179

Text #2

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.9759. Min Act: -0.0000

Data Index: 1399409 (The Pile)

Max Activating Token Index: 854

Text #3

Max Range: 1.0670. Min Range: -1.0670

Max Act: 1.0250. Min Act: -0.0000

Data Index: 477684 (The Pile)

Max Activating Token Index: 966

Text #4

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.8818. Min Act: -0.0000

Data Index: 1398458 (The Pile)

Max Activating Token Index: 37

Text #5

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.8825. Min Act: -0.0000

Data Index: 1878392 (The Pile)

Max Activating Token Index: 321

Text #6

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.8632. Min Act: -0.0000

Data Index: 700905 (The Pile)

Max Activating Token Index: 294

Text #7

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.9546. Min Act: -0.0000

Data Index: 1741648 (The Pile)

Max Activating Token Index: 34

Text #8

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1948998 (The Pile)

Max Activating Token Index: 873

Text #9

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.8390. Min Act: -0.0000

Data Index: 1101986 (The Pile)

Max Activating Token Index: 881

Text #10

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.7699. Min Act: -0.0000

Data Index: 1138510 (The Pile)

Max Activating Token Index: 51

Text #11

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.7836. Min Act: -0.0000

Data Index: 1700977 (The Pile)

Max Activating Token Index: 86

Text #12

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.7482. Min Act: -0.0000

Data Index: 621384 (The Pile)

Max Activating Token Index: 379

Text #13

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.7801. Min Act: -0.0000

Data Index: 1003956 (The Pile)

Max Activating Token Index: 200

Text #14

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.7488. Min Act: -0.0000

Data Index: 703457 (The Pile)

Max Activating Token Index: 204

Text #15

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.7465. Min Act: -0.0000

Data Index: 803322 (The Pile)

Max Activating Token Index: 790

Text #16

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.7875. Min Act: -0.0000

Data Index: 52925 (The Pile)

Max Activating Token Index: 444

Text #17

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.7251. Min Act: -0.0000

Data Index: 842416 (The Pile)

Max Activating Token Index: 104

Text #18

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.7543. Min Act: -0.0000

Data Index: 222006 (The Pile)

Max Activating Token Index: 281

Text #19

Max Range: 1.0670. Min Range: -1.0670

Max Act: 0.7946. Min Act: -0.0000

Data Index: 1016082 (The Pile)

Max Activating Token Index: 30