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

Dataset: The Pile

Neuron 1916 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: 1.2507. Min Range: -1.2507

Max Act: 1.0109. Min Act: -0.0000

Data Index: 633715 (The Pile)

Max Activating Token Index: 890

Text #1

Max Range: 1.2507. Min Range: -1.2507

Max Act: 1.2507. Min Act: -0.0000

Data Index: 557564 (The Pile)

Max Activating Token Index: 856

Text #2

Max Range: 1.2507. Min Range: -1.2507

Max Act: 1.1026. Min Act: -0.0000

Data Index: 569854 (The Pile)

Max Activating Token Index: 275

Text #3

Max Range: 1.2507. Min Range: -1.2507

Max Act: 1.0988. Min Act: -0.0000

Data Index: 108302 (The Pile)

Max Activating Token Index: 777

Text #4

Max Range: 1.2507. Min Range: -1.2507

Max Act: 1.1075. Min Act: -0.0000

Data Index: 1491764 (The Pile)

Max Activating Token Index: 488

Text #5

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.9632. Min Act: -0.0000

Data Index: 771002 (The Pile)

Max Activating Token Index: 327

Text #6

Max Range: 1.2507. Min Range: -1.2507

Max Act: 1.0224. Min Act: -0.0000

Data Index: 1445671 (The Pile)

Max Activating Token Index: 390

Text #7

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.9700. Min Act: -0.0000

Data Index: 497258 (The Pile)

Max Activating Token Index: 471

Text #8

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.9704. Min Act: -0.0000

Data Index: 1672824 (The Pile)

Max Activating Token Index: 767

Text #9

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.9607. Min Act: -0.0000

Data Index: 357271 (The Pile)

Max Activating Token Index: 148

Text #10

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.9527. Min Act: -0.0000

Data Index: 1326093 (The Pile)

Max Activating Token Index: 189

Text #11

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.9075. Min Act: -0.0000

Data Index: 1403238 (The Pile)

Max Activating Token Index: 1022

Text #12

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.8899. Min Act: -0.0000

Data Index: 883191 (The Pile)

Max Activating Token Index: 879

Text #13

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.9820. Min Act: -0.0000

Data Index: 1265745 (The Pile)

Max Activating Token Index: 200

Text #14

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.9449. Min Act: -0.0000

Data Index: 661986 (The Pile)

Max Activating Token Index: 495

Text #15

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.9479. Min Act: -0.0000

Data Index: 1192154 (The Pile)

Max Activating Token Index: 898

Text #16

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.9911. Min Act: -0.0000

Data Index: 590560 (The Pile)

Max Activating Token Index: 517

Text #17

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.8856. Min Act: -0.0000

Data Index: 957348 (The Pile)

Max Activating Token Index: 501

Text #18

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.8993. Min Act: -0.0000

Data Index: 1992504 (The Pile)

Max Activating Token Index: 187

Text #19

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.8852. Min Act: -0.0000

Data Index: 1091765 (The Pile)

Max Activating Token Index: 734