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

Dataset: The Pile

Neuron 4317 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: 1.2455. Min Range: -1.2455

Max Act: 1.2455. Min Act: -0.0000

Data Index: 1849177 (The Pile)

Max Activating Token Index: 816

Text #1

Max Range: 1.2455. Min Range: -1.2455

Max Act: 1.1483. Min Act: -0.0000

Data Index: 1972363 (The Pile)

Max Activating Token Index: 501

Text #2

Max Range: 1.2455. Min Range: -1.2455

Max Act: 1.1531. Min Act: -0.0000

Data Index: 853242 (The Pile)

Max Activating Token Index: 653

Text #3

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8999. Min Act: -0.0000

Data Index: 746813 (The Pile)

Max Activating Token Index: 822

Text #4

Max Range: 1.2455. Min Range: -1.2455

Max Act: 1.1004. Min Act: -0.0000

Data Index: 1873483 (The Pile)

Max Activating Token Index: 234

Text #5

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.9949. Min Act: -0.0001

Data Index: 1311728 (The Pile)

Max Activating Token Index: 204

Text #6

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.9773. Min Act: -0.0000

Data Index: 1707329 (The Pile)

Max Activating Token Index: 281

Text #7

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8975. Min Act: -0.0000

Data Index: 939634 (The Pile)

Max Activating Token Index: 372

Text #8

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.6027. Min Act: -0.0000

Data Index: 1973323 (The Pile)

Max Activating Token Index: 920

Text #9

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7074. Min Act: -0.0000

Data Index: 1677280 (The Pile)

Max Activating Token Index: 773

Text #10

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8317. Min Act: -0.0000

Data Index: 944840 (The Pile)

Max Activating Token Index: 55

Text #11

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7679. Min Act: -0.0001

Data Index: 1237246 (The Pile)

Max Activating Token Index: 433

Text #12

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.6971. Min Act: -0.0000

Data Index: 730311 (The Pile)

Max Activating Token Index: 80

Text #13

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7426. Min Act: -0.0000

Data Index: 923815 (The Pile)

Max Activating Token Index: 885

Text #14

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7111. Min Act: -0.0000

Data Index: 1845299 (The Pile)

Max Activating Token Index: 227

Text #15

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.9759. Min Act: -0.0001

Data Index: 1366384 (The Pile)

Max Activating Token Index: 738

Text #16

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7783. Min Act: -0.0000

Data Index: 1320336 (The Pile)

Max Activating Token Index: 1019

Text #17

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7236. Min Act: -0.0000

Data Index: 974829 (The Pile)

Max Activating Token Index: 119

Text #18

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7875. Min Act: -0.0000

Data Index: 659128 (The Pile)

Max Activating Token Index: 354

Text #19

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8023. Min Act: -0.0000

Data Index: 1280276 (The Pile)

Max Activating Token Index: 586