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

Dataset: The Pile

Neuron 1092 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: 0.7434. Min Range: -0.7434

Max Act: 0.7434. Min Act: -0.0000

Data Index: 1292097 (The Pile)

Max Activating Token Index: 666

Text #1

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1033721 (The Pile)

Max Activating Token Index: 655

Text #2

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.6085. Min Act: -0.0000

Data Index: 1061675 (The Pile)

Max Activating Token Index: 325

Text #3

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.5798. Min Act: 0.0000

Data Index: 1821007 (The Pile)

Max Activating Token Index: 278

Text #4

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.5850. Min Act: -0.0000

Data Index: 1331230 (The Pile)

Max Activating Token Index: 858

Text #5

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.5555. Min Act: 0.0000

Data Index: 1950923 (The Pile)

Max Activating Token Index: 33

Text #6

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.5040. Min Act: -0.0000

Data Index: 1747545 (The Pile)

Max Activating Token Index: 934

Text #7

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.5124. Min Act: -0.0000

Data Index: 169951 (The Pile)

Max Activating Token Index: 632

Text #8

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.5094. Min Act: -0.0000

Data Index: 323644 (The Pile)

Max Activating Token Index: 950

Text #9

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.5084. Min Act: -0.0000

Data Index: 1849465 (The Pile)

Max Activating Token Index: 535

Text #10

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1343020 (The Pile)

Max Activating Token Index: 307

Text #11

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.5053. Min Act: -0.0000

Data Index: 1565579 (The Pile)

Max Activating Token Index: 760

Text #12

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.4901. Min Act: -0.0000

Data Index: 1323925 (The Pile)

Max Activating Token Index: 535

Text #13

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.4925. Min Act: -0.0000

Data Index: 832901 (The Pile)

Max Activating Token Index: 665

Text #14

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1725772 (The Pile)

Max Activating Token Index: 254

Text #15

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.4623. Min Act: -0.0000

Data Index: 357338 (The Pile)

Max Activating Token Index: 75

Text #16

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.4706. Min Act: -0.0000

Data Index: 832994 (The Pile)

Max Activating Token Index: 457

Text #17

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.4970. Min Act: -0.0000

Data Index: 1516816 (The Pile)

Max Activating Token Index: 937

Text #18

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.5001. Min Act: -0.0000

Data Index: 1359505 (The Pile)

Max Activating Token Index: 145

Text #19

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.4785. Min Act: -0.0000

Data Index: 470097 (The Pile)

Max Activating Token Index: 60