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

Dataset: The Pile

Neuron 700 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1030. Min Range: -1.1030

Max Act: 1.1030. Min Act: -0.0000

Data Index: 1759029 (The Pile)

Max Activating Token Index: 531

Text #1

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.9805. Min Act: -0.0000

Data Index: 138693 (The Pile)

Max Activating Token Index: 229

Text #2

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.9245. Min Act: -0.0000

Data Index: 1854697 (The Pile)

Max Activating Token Index: 528

Text #3

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8868. Min Act: -0.0000

Data Index: 998009 (The Pile)

Max Activating Token Index: 18

Text #4

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1517601 (The Pile)

Max Activating Token Index: 514

Text #5

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8769. Min Act: -0.0000

Data Index: 1093997 (The Pile)

Max Activating Token Index: 609

Text #6

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8039. Min Act: -0.0000

Data Index: 1101544 (The Pile)

Max Activating Token Index: 426

Text #7

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8681. Min Act: -0.0000

Data Index: 822118 (The Pile)

Max Activating Token Index: 300

Text #8

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8498. Min Act: 0.0000

Data Index: 713720 (The Pile)

Max Activating Token Index: 240

Text #9

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8588. Min Act: -0.0000

Data Index: 347839 (The Pile)

Max Activating Token Index: 609

Text #10

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7129. Min Act: -0.0000

Data Index: 171435 (The Pile)

Max Activating Token Index: 919

Text #11

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7746. Min Act: 0.0000

Data Index: 1655127 (The Pile)

Max Activating Token Index: 727

Text #12

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7465. Min Act: -0.0000

Data Index: 765764 (The Pile)

Max Activating Token Index: 601

Text #13

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7680. Min Act: -0.0000

Data Index: 610344 (The Pile)

Max Activating Token Index: 417

Text #14

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1190631 (The Pile)

Max Activating Token Index: 355

Text #15

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7354. Min Act: -0.0000

Data Index: 862611 (The Pile)

Max Activating Token Index: 217

Text #16

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7331. Min Act: -0.0000

Data Index: 1318603 (The Pile)

Max Activating Token Index: 896

Text #17

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7592. Min Act: -0.0000

Data Index: 1190156 (The Pile)

Max Activating Token Index: 507

Text #18

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7789. Min Act: -0.0000

Data Index: 713436 (The Pile)

Max Activating Token Index: 707

Text #19

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7540. Min Act: -0.0000

Data Index: 1256202 (The Pile)

Max Activating Token Index: 655