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

Dataset: The Pile

Neuron 3096 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: 1.8650. Min Range: -1.8650

Max Act: 1.6496. Min Act: -0.0000

Data Index: 1394563 (The Pile)

Max Activating Token Index: 650

Text #1

Max Range: 1.8650. Min Range: -1.8650

Max Act: 1.8058. Min Act: -0.0000

Data Index: 1921959 (The Pile)

Max Activating Token Index: 929

Text #2

Max Range: 1.8650. Min Range: -1.8650

Max Act: 1.6698. Min Act: -0.0000

Data Index: 1820424 (The Pile)

Max Activating Token Index: 489

Text #3

Max Range: 1.8650. Min Range: -1.8650

Max Act: 1.7616. Min Act: -0.0000

Data Index: 166695 (The Pile)

Max Activating Token Index: 652

Text #4

Max Range: 1.8650. Min Range: -1.8650

Max Act: 1.8591. Min Act: -0.0000

Data Index: 934233 (The Pile)

Max Activating Token Index: 258

Text #5

Max Range: 1.8650. Min Range: -1.8650

Max Act: 1.6339. Min Act: -0.0000

Data Index: 1063664 (The Pile)

Max Activating Token Index: 526

Text #6

Max Range: 1.8650. Min Range: -1.8650

Max Act: 1.5308. Min Act: -0.0000

Data Index: 1686237 (The Pile)

Max Activating Token Index: 263

Text #7

Max Range: 1.8650. Min Range: -1.8650

Max Act: 1.8650. Min Act: -0.0000

Data Index: 616262 (The Pile)

Max Activating Token Index: 856

Text #8

Max Range: 1.8650. Min Range: -1.8650

Max Act: 1.7333. Min Act: -0.0000

Data Index: 1368881 (The Pile)

Max Activating Token Index: 299

Text #9

Max Range: 1.8650. Min Range: -1.8650

Max Act: 1.5464. Min Act: -0.0000

Data Index: 109898 (The Pile)

Max Activating Token Index: 274

Text #10

Max Range: 1.8650. Min Range: -1.8650

Max Act: 1.2281. Min Act: -0.0000

Data Index: 339863 (The Pile)

Max Activating Token Index: 802

Text #11

Max Range: 1.8650. Min Range: -1.8650

Max Act: 1.5318. Min Act: -0.0000

Data Index: 1958184 (The Pile)

Max Activating Token Index: 187

Text #12

Max Range: 1.8650. Min Range: -1.8650

Max Act: 1.6155. Min Act: -0.0000

Data Index: 1638673 (The Pile)

Max Activating Token Index: 698

Text #13

Max Range: 1.8650. Min Range: -1.8650

Max Act: 1.5182. Min Act: -0.0000

Data Index: 766315 (The Pile)

Max Activating Token Index: 238

Text #14

Max Range: 1.8650. Min Range: -1.8650

Max Act: 1.4668. Min Act: -0.0000

Data Index: 813333 (The Pile)

Max Activating Token Index: 629

Text #15

Max Range: 1.8650. Min Range: -1.8650

Max Act: 1.7893. Min Act: -0.0000

Data Index: 1007611 (The Pile)

Max Activating Token Index: 706

Text #16

Max Range: 1.8650. Min Range: -1.8650

Max Act: 1.5028. Min Act: -0.0000

Data Index: 1153663 (The Pile)

Max Activating Token Index: 574

Text #17

Max Range: 1.8650. Min Range: -1.8650

Max Act: 1.6600. Min Act: -0.0000

Data Index: 1107286 (The Pile)

Max Activating Token Index: 459

Text #18

Max Range: 1.8650. Min Range: -1.8650

Max Act: 1.5612. Min Act: -0.0000

Data Index: 1548698 (The Pile)

Max Activating Token Index: 682

Text #19

Max Range: 1.8650. Min Range: -1.8650

Max Act: 1.6590. Min Act: -0.0000

Data Index: 138130 (The Pile)

Max Activating Token Index: 486