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

Dataset: The Pile

Neuron 2557 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.5417. Min Act: -0.0000

Data Index: 571027 (The Pile)

Max Activating Token Index: 95

Text #1

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1585660 (The Pile)

Max Activating Token Index: 483

Text #2

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4988. Min Act: -0.0000

Data Index: 534023 (The Pile)

Max Activating Token Index: 348

Text #3

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4645. Min Act: -0.0000

Data Index: 1506959 (The Pile)

Max Activating Token Index: 99

Text #4

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4432. Min Act: -0.0000

Data Index: 1084548 (The Pile)

Max Activating Token Index: 900

Text #5

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1876157 (The Pile)

Max Activating Token Index: 67

Text #6

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4580. Min Act: -0.0000

Data Index: 62179 (The Pile)

Max Activating Token Index: 126

Text #7

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4245. Min Act: -0.0000

Data Index: 1372118 (The Pile)

Max Activating Token Index: 94

Text #8

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4256. Min Act: -0.0000

Data Index: 1267212 (The Pile)

Max Activating Token Index: 199

Text #9

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4391. Min Act: -0.0000

Data Index: 1330366 (The Pile)

Max Activating Token Index: 561

Text #10

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4120. Min Act: -0.0000

Data Index: 79269 (The Pile)

Max Activating Token Index: 958

Text #11

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4377. Min Act: -0.0000

Data Index: 969262 (The Pile)

Max Activating Token Index: 251

Text #12

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4427. Min Act: -0.0000

Data Index: 1372882 (The Pile)

Max Activating Token Index: 103

Text #13

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4155. Min Act: -0.0000

Data Index: 373184 (The Pile)

Max Activating Token Index: 594

Text #14

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3988. Min Act: -0.0000

Data Index: 1115665 (The Pile)

Max Activating Token Index: 555

Text #15

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4014. Min Act: -0.0000

Data Index: 1236500 (The Pile)

Max Activating Token Index: 694

Text #16

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3860. Min Act: -0.0000

Data Index: 628823 (The Pile)

Max Activating Token Index: 611

Text #17

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3970. Min Act: -0.0000

Data Index: 1488165 (The Pile)

Max Activating Token Index: 708

Text #18

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4038. Min Act: -0.0000

Data Index: 1621724 (The Pile)

Max Activating Token Index: 124

Text #19

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3852. Min Act: -0.0000

Data Index: 1917983 (The Pile)

Max Activating Token Index: 540