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

Dataset: The Pile

Neuron 1697 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: 0.6150. Min Range: -0.6150

Max Act: 0.6150. Min Act: -0.0000

Data Index: 600693 (The Pile)

Max Activating Token Index: 610

Text #1

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1833002 (The Pile)

Max Activating Token Index: 516

Text #2

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5790. Min Act: -0.0000

Data Index: 341425 (The Pile)

Max Activating Token Index: 528

Text #3

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5782. Min Act: 0.0000

Data Index: 245731 (The Pile)

Max Activating Token Index: 787

Text #4

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5596. Min Act: -0.0000

Data Index: 1101726 (The Pile)

Max Activating Token Index: 739

Text #5

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5404. Min Act: -0.0000

Data Index: 1300793 (The Pile)

Max Activating Token Index: 415

Text #6

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5486. Min Act: -0.0000

Data Index: 1559183 (The Pile)

Max Activating Token Index: 918

Text #7

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5353. Min Act: -0.0000

Data Index: 1493399 (The Pile)

Max Activating Token Index: 706

Text #8

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5201. Min Act: -0.0000

Data Index: 145047 (The Pile)

Max Activating Token Index: 737

Text #9

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1676874 (The Pile)

Max Activating Token Index: 329

Text #10

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5034. Min Act: 0.0000

Data Index: 724551 (The Pile)

Max Activating Token Index: 225

Text #11

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5346. Min Act: -0.0000

Data Index: 1632598 (The Pile)

Max Activating Token Index: 569

Text #12

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5456. Min Act: 0.0000

Data Index: 1180767 (The Pile)

Max Activating Token Index: 558

Text #13

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5341. Min Act: -0.0000

Data Index: 1844279 (The Pile)

Max Activating Token Index: 386

Text #14

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5369. Min Act: -0.0000

Data Index: 724476 (The Pile)

Max Activating Token Index: 890

Text #15

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5216. Min Act: -0.0000

Data Index: 1590050 (The Pile)

Max Activating Token Index: 786

Text #16

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5175. Min Act: -0.0000

Data Index: 1267836 (The Pile)

Max Activating Token Index: 547

Text #17

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5118. Min Act: -0.0000

Data Index: 734488 (The Pile)

Max Activating Token Index: 798

Text #18

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5122. Min Act: -0.0000

Data Index: 1800203 (The Pile)

Max Activating Token Index: 257

Text #19

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.4915. Min Act: 0.0001

Data Index: 92429 (The Pile)

Max Activating Token Index: 483