Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4363 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5007. Min Range: -1.5007

Max Act: 1.5007. Min Act: -0.0000

Data Index: 880278 (The Pile)

Max Activating Token Index: 503

Text #1

Max Range: 1.5007. Min Range: -1.5007

Max Act: 1.3931. Min Act: -0.0000

Data Index: 1453584 (The Pile)

Max Activating Token Index: 478

Text #2

Max Range: 1.5007. Min Range: -1.5007

Max Act: 1.2927. Min Act: -0.0000

Data Index: 1771229 (The Pile)

Max Activating Token Index: 361

Text #3

Max Range: 1.5007. Min Range: -1.5007

Max Act: 1.2450. Min Act: -0.0000

Data Index: 1265565 (The Pile)

Max Activating Token Index: 6

Text #4

Max Range: 1.5007. Min Range: -1.5007

Max Act: 1.1075. Min Act: -0.0000

Data Index: 840542 (The Pile)

Max Activating Token Index: 371

Text #5

Max Range: 1.5007. Min Range: -1.5007

Max Act: 1.1289. Min Act: -0.0000

Data Index: 544379 (The Pile)

Max Activating Token Index: 214

Text #6

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.9962. Min Act: -0.0000

Data Index: 1555052 (The Pile)

Max Activating Token Index: 112

Text #7

Max Range: 1.5007. Min Range: -1.5007

Max Act: 1.0217. Min Act: -0.0000

Data Index: 706274 (The Pile)

Max Activating Token Index: 499

Text #8

Max Range: 1.5007. Min Range: -1.5007

Max Act: 1.0520. Min Act: -0.0000

Data Index: 1736663 (The Pile)

Max Activating Token Index: 725

Text #9

Max Range: 1.5007. Min Range: -1.5007

Max Act: 1.1053. Min Act: -0.0000

Data Index: 56231 (The Pile)

Max Activating Token Index: 345

Text #10

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.9876. Min Act: -0.0000

Data Index: 1736472 (The Pile)

Max Activating Token Index: 19

Text #11

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.9756. Min Act: -0.0000

Data Index: 217317 (The Pile)

Max Activating Token Index: 9

Text #12

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.9630. Min Act: -0.0000

Data Index: 570821 (The Pile)

Max Activating Token Index: 678

Text #13

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.9864. Min Act: -0.0000

Data Index: 650521 (The Pile)

Max Activating Token Index: 164

Text #14

Max Range: 1.5007. Min Range: -1.5007

Max Act: 1.0148. Min Act: -0.0000

Data Index: 816222 (The Pile)

Max Activating Token Index: 157

Text #15

Max Range: 1.5007. Min Range: -1.5007

Max Act: 1.0136. Min Act: -0.0000

Data Index: 357626 (The Pile)

Max Activating Token Index: 1012

Text #16

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.8875. Min Act: -0.0000

Data Index: 848626 (The Pile)

Max Activating Token Index: 228

Text #17

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.9764. Min Act: -0.0000

Data Index: 1246950 (The Pile)

Max Activating Token Index: 234

Text #18

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.8518. Min Act: -0.0000

Data Index: 1910027 (The Pile)

Max Activating Token Index: 91

Text #19

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.9988. Min Act: -0.0000

Data Index: 713728 (The Pile)

Max Activating Token Index: 18