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

Dataset: The Pile

Neuron 4373 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: 0.9898. Min Range: -0.9898

Max Act: 0.9898. Min Act: -0.0000

Data Index: 249982 (The Pile)

Max Activating Token Index: 657

Text #1

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.9865. Min Act: -0.0000

Data Index: 15443 (The Pile)

Max Activating Token Index: 826

Text #2

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.9172. Min Act: -0.0000

Data Index: 1280977 (The Pile)

Max Activating Token Index: 328

Text #3

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.9084. Min Act: -0.0000

Data Index: 1587528 (The Pile)

Max Activating Token Index: 284

Text #4

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.8522. Min Act: -0.0000

Data Index: 463536 (The Pile)

Max Activating Token Index: 272

Text #5

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.8494. Min Act: -0.0000

Data Index: 1745196 (The Pile)

Max Activating Token Index: 641

Text #6

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.8433. Min Act: -0.0000

Data Index: 1789971 (The Pile)

Max Activating Token Index: 395

Text #7

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.7876. Min Act: -0.0000

Data Index: 748405 (The Pile)

Max Activating Token Index: 99

Text #8

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.8345. Min Act: -0.0000

Data Index: 227218 (The Pile)

Max Activating Token Index: 351

Text #9

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.8026. Min Act: -0.0000

Data Index: 1551386 (The Pile)

Max Activating Token Index: 671

Text #10

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.6467. Min Act: -0.0000

Data Index: 1673639 (The Pile)

Max Activating Token Index: 845

Text #11

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.7847. Min Act: -0.0000

Data Index: 259052 (The Pile)

Max Activating Token Index: 614

Text #12

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.7820. Min Act: -0.0000

Data Index: 1445586 (The Pile)

Max Activating Token Index: 499

Text #13

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.7788. Min Act: -0.0000

Data Index: 1467104 (The Pile)

Max Activating Token Index: 973

Text #14

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.8349. Min Act: -0.0000

Data Index: 1066686 (The Pile)

Max Activating Token Index: 922

Text #15

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.7138. Min Act: -0.0000

Data Index: 1686575 (The Pile)

Max Activating Token Index: 948

Text #16

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.7650. Min Act: -0.0000

Data Index: 539152 (The Pile)

Max Activating Token Index: 657

Text #17

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.8054. Min Act: -0.0000

Data Index: 934161 (The Pile)

Max Activating Token Index: 134

Text #18

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.8230. Min Act: -0.0000

Data Index: 989385 (The Pile)

Max Activating Token Index: 94

Text #19

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.6970. Min Act: -0.0000

Data Index: 1086344 (The Pile)

Max Activating Token Index: 713