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

Dataset: The Pile

Neuron 2376 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: 0.9216. Min Range: -0.9216

Max Act: 0.9216. Min Act: -0.0000

Data Index: 849608 (The Pile)

Max Activating Token Index: 191

Text #1

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8103. Min Act: -0.0000

Data Index: 1816588 (The Pile)

Max Activating Token Index: 701

Text #2

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8016. Min Act: -0.0000

Data Index: 531585 (The Pile)

Max Activating Token Index: 532

Text #3

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8641. Min Act: -0.0000

Data Index: 681495 (The Pile)

Max Activating Token Index: 578

Text #4

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7379. Min Act: -0.0000

Data Index: 1394731 (The Pile)

Max Activating Token Index: 681

Text #5

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7806. Min Act: -0.0000

Data Index: 1238382 (The Pile)

Max Activating Token Index: 333

Text #6

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7301. Min Act: -0.0000

Data Index: 1977423 (The Pile)

Max Activating Token Index: 753

Text #7

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.6571. Min Act: -0.0000

Data Index: 658804 (The Pile)

Max Activating Token Index: 841

Text #8

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.6928. Min Act: -0.0000

Data Index: 908020 (The Pile)

Max Activating Token Index: 808

Text #9

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1692624 (The Pile)

Max Activating Token Index: 135

Text #10

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1790833 (The Pile)

Max Activating Token Index: 616

Text #11

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7104. Min Act: -0.0000

Data Index: 1270801 (The Pile)

Max Activating Token Index: 863

Text #12

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.6216. Min Act: -0.0000

Data Index: 1917311 (The Pile)

Max Activating Token Index: 736

Text #13

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.5986. Min Act: -0.0000

Data Index: 1597092 (The Pile)

Max Activating Token Index: 877

Text #14

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1859065 (The Pile)

Max Activating Token Index: 700

Text #15

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.6029. Min Act: 0.0000

Data Index: 1043101 (The Pile)

Max Activating Token Index: 751

Text #16

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.5671. Min Act: -0.0000

Data Index: 39022 (The Pile)

Max Activating Token Index: 938

Text #17

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.5895. Min Act: 0.0000

Data Index: 33223 (The Pile)

Max Activating Token Index: 166

Text #18

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.5731. Min Act: -0.0000

Data Index: 960403 (The Pile)

Max Activating Token Index: 397

Text #19

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1722945 (The Pile)

Max Activating Token Index: 262