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

Dataset: The Pile

Neuron 1390 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.7280. Min Act: -0.0000

Data Index: 317911 (The Pile)

Max Activating Token Index: 952

Text #1

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.8011. Min Act: -0.0000

Data Index: 1689929 (The Pile)

Max Activating Token Index: 634

Text #2

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.7261. Min Act: -0.0000

Data Index: 1502332 (The Pile)

Max Activating Token Index: 589

Text #3

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.6878. Min Act: -0.0000

Data Index: 274229 (The Pile)

Max Activating Token Index: 365

Text #4

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.7185. Min Act: -0.0000

Data Index: 1638160 (The Pile)

Max Activating Token Index: 979

Text #5

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.6658. Min Act: -0.0000

Data Index: 1397053 (The Pile)

Max Activating Token Index: 694

Text #6

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.6929. Min Act: -0.0000

Data Index: 1404494 (The Pile)

Max Activating Token Index: 168

Text #7

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.6673. Min Act: -0.0000

Data Index: 664571 (The Pile)

Max Activating Token Index: 417

Text #8

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.7030. Min Act: -0.0000

Data Index: 97438 (The Pile)

Max Activating Token Index: 348

Text #9

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.6168. Min Act: -0.0000

Data Index: 165310 (The Pile)

Max Activating Token Index: 879

Text #10

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.5980. Min Act: -0.0000

Data Index: 1024313 (The Pile)

Max Activating Token Index: 361

Text #11

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.6298. Min Act: -0.0000

Data Index: 1277941 (The Pile)

Max Activating Token Index: 535

Text #12

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1758339 (The Pile)

Max Activating Token Index: 835

Text #13

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.6291. Min Act: -0.0000

Data Index: 1238710 (The Pile)

Max Activating Token Index: 999

Text #14

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1822711 (The Pile)

Max Activating Token Index: 100

Text #15

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.5981. Min Act: -0.0000

Data Index: 1919225 (The Pile)

Max Activating Token Index: 846

Text #16

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.6149. Min Act: -0.0000

Data Index: 413468 (The Pile)

Max Activating Token Index: 687

Text #17

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.5723. Min Act: -0.0000

Data Index: 757787 (The Pile)

Max Activating Token Index: 825

Text #18

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1656008 (The Pile)

Max Activating Token Index: 888

Text #19

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.5996. Min Act: -0.0000

Data Index: 570879 (The Pile)

Max Activating Token Index: 352