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

Dataset: The Pile

Neuron 2582 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0657. Min Range: -1.0657

Max Act: 1.0657. Min Act: -0.0000

Data Index: 1862880 (The Pile)

Max Activating Token Index: 1017

Text #1

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.9006. Min Act: -0.0000

Data Index: 891153 (The Pile)

Max Activating Token Index: 121

Text #2

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.9481. Min Act: 0.0000

Data Index: 765984 (The Pile)

Max Activating Token Index: 215

Text #3

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.9111. Min Act: -0.0000

Data Index: 766702 (The Pile)

Max Activating Token Index: 121

Text #4

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.8624. Min Act: -0.0000

Data Index: 1130855 (The Pile)

Max Activating Token Index: 919

Text #5

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.8882. Min Act: -0.0000

Data Index: 1222248 (The Pile)

Max Activating Token Index: 30

Text #6

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.8100. Min Act: -0.0000

Data Index: 1684999 (The Pile)

Max Activating Token Index: 225

Text #7

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.7650. Min Act: 0.0000

Data Index: 872171 (The Pile)

Max Activating Token Index: 265

Text #8

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.7698. Min Act: -0.0000

Data Index: 444163 (The Pile)

Max Activating Token Index: 122

Text #9

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.7454. Min Act: -0.0000

Data Index: 1397788 (The Pile)

Max Activating Token Index: 34

Text #10

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1464592 (The Pile)

Max Activating Token Index: 216

Text #11

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.7094. Min Act: -0.0000

Data Index: 1926544 (The Pile)

Max Activating Token Index: 50

Text #12

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.7054. Min Act: -0.0000

Data Index: 1314175 (The Pile)

Max Activating Token Index: 120

Text #13

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.7463. Min Act: -0.0000

Data Index: 1571388 (The Pile)

Max Activating Token Index: 45

Text #14

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.6527. Min Act: -0.0000

Data Index: 1316163 (The Pile)

Max Activating Token Index: 837

Text #15

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.7117. Min Act: -0.0000

Data Index: 644542 (The Pile)

Max Activating Token Index: 97

Text #16

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.7331. Min Act: -0.0000

Data Index: 159694 (The Pile)

Max Activating Token Index: 51

Text #17

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.6612. Min Act: -0.0000

Data Index: 603802 (The Pile)

Max Activating Token Index: 179

Text #18

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.7110. Min Act: -0.0000

Data Index: 1417185 (The Pile)

Max Activating Token Index: 121

Text #19

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.7568. Min Act: -0.0000

Data Index: 1232391 (The Pile)

Max Activating Token Index: 123