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

Dataset: The Pile

Neuron 1855 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.0305. Min Range: -9.0305

Max Act: 9.0305. Min Act: -0.0000

Data Index: 1872292 (The Pile)

Max Activating Token Index: 407

Text #1

Max Range: 9.0305. Min Range: -9.0305

Max Act: 8.9199. Min Act: -0.0000

Data Index: 877177 (The Pile)

Max Activating Token Index: 395

Text #2

Max Range: 9.0305. Min Range: -9.0305

Max Act: 8.7706. Min Act: -0.0000

Data Index: 473342 (The Pile)

Max Activating Token Index: 519

Text #3

Max Range: 9.0305. Min Range: -9.0305

Max Act: 8.7326. Min Act: -0.0000

Data Index: 1442853 (The Pile)

Max Activating Token Index: 480

Text #4

Max Range: 9.0305. Min Range: -9.0305

Max Act: 8.6960. Min Act: -0.0000

Data Index: 1681993 (The Pile)

Max Activating Token Index: 119

Text #5

Max Range: 9.0305. Min Range: -9.0305

Max Act: 8.3804. Min Act: -0.0000

Data Index: 655751 (The Pile)

Max Activating Token Index: 322

Text #6

Max Range: 9.0305. Min Range: -9.0305

Max Act: 8.6674. Min Act: -0.0000

Data Index: 727480 (The Pile)

Max Activating Token Index: 247

Text #7

Max Range: 9.0305. Min Range: -9.0305

Max Act: 8.5082. Min Act: -0.0000

Data Index: 119017 (The Pile)

Max Activating Token Index: 816

Text #8

Max Range: 9.0305. Min Range: -9.0305

Max Act: 8.5958. Min Act: -0.0000

Data Index: 407341 (The Pile)

Max Activating Token Index: 434

Text #9

Max Range: 9.0305. Min Range: -9.0305

Max Act: 8.4268. Min Act: -0.0000

Data Index: 59739 (The Pile)

Max Activating Token Index: 553

Text #10

Max Range: 9.0305. Min Range: -9.0305

Max Act: 8.2448. Min Act: -0.0000

Data Index: 1375670 (The Pile)

Max Activating Token Index: 971

Text #11

Max Range: 9.0305. Min Range: -9.0305

Max Act: 8.3637. Min Act: -0.0000

Data Index: 392736 (The Pile)

Max Activating Token Index: 150

Text #12

Max Range: 9.0305. Min Range: -9.0305

Max Act: 8.4752. Min Act: -0.0000

Data Index: 174359 (The Pile)

Max Activating Token Index: 570

Text #13

Max Range: 9.0305. Min Range: -9.0305

Max Act: 8.4665. Min Act: -0.0000

Data Index: 1501471 (The Pile)

Max Activating Token Index: 41

Text #14

Max Range: 9.0305. Min Range: -9.0305

Max Act: 8.2842. Min Act: -0.0000

Data Index: 1423685 (The Pile)

Max Activating Token Index: 371

Text #15

Max Range: 9.0305. Min Range: -9.0305

Max Act: 8.2178. Min Act: -0.0000

Data Index: 283214 (The Pile)

Max Activating Token Index: 443

Text #16

Max Range: 9.0305. Min Range: -9.0305

Max Act: 8.2157. Min Act: -0.0000

Data Index: 805794 (The Pile)

Max Activating Token Index: 881

Text #17

Max Range: 9.0305. Min Range: -9.0305

Max Act: 8.1858. Min Act: -0.0000

Data Index: 28045 (The Pile)

Max Activating Token Index: 94

Text #18

Max Range: 9.0305. Min Range: -9.0305

Max Act: 8.2086. Min Act: -0.0000

Data Index: 1257938 (The Pile)

Max Activating Token Index: 213

Text #19

Max Range: 9.0305. Min Range: -9.0305

Max Act: 8.1753. Min Act: -0.0000

Data Index: 1106122 (The Pile)

Max Activating Token Index: 71