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

Dataset: The Pile

Neuron 1532 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: 5.0197. Min Range: -5.0197

Max Act: 5.0197. Min Act: -0.0000

Data Index: 655209 (The Pile)

Max Activating Token Index: 411

Text #1

Max Range: 5.0197. Min Range: -5.0197

Max Act: 4.7612. Min Act: -0.0000

Data Index: 1205339 (The Pile)

Max Activating Token Index: 74

Text #2

Max Range: 5.0197. Min Range: -5.0197

Max Act: 4.4972. Min Act: -0.0000

Data Index: 1140802 (The Pile)

Max Activating Token Index: 20

Text #3

Max Range: 5.0197. Min Range: -5.0197

Max Act: 4.2520. Min Act: -0.0000

Data Index: 1859971 (The Pile)

Max Activating Token Index: 26

Text #4

Max Range: 5.0197. Min Range: -5.0197

Max Act: 4.0955. Min Act: -0.0000

Data Index: 1718756 (The Pile)

Max Activating Token Index: 29

Text #5

Max Range: 5.0197. Min Range: -5.0197

Max Act: 4.0018. Min Act: -0.0000

Data Index: 1093976 (The Pile)

Max Activating Token Index: 366

Text #6

Max Range: 5.0197. Min Range: -5.0197

Max Act: 3.9666. Min Act: -0.0000

Data Index: 1511777 (The Pile)

Max Activating Token Index: 123

Text #7

Max Range: 5.0197. Min Range: -5.0197

Max Act: 4.2847. Min Act: -0.0000

Data Index: 1920453 (The Pile)

Max Activating Token Index: 122

Text #8

Max Range: 5.0197. Min Range: -5.0197

Max Act: 4.2497. Min Act: -0.0000

Data Index: 1062040 (The Pile)

Max Activating Token Index: 598

Text #9

Max Range: 5.0197. Min Range: -5.0197

Max Act: 3.9953. Min Act: -0.0000

Data Index: 716327 (The Pile)

Max Activating Token Index: 46

Text #10

Max Range: 5.0197. Min Range: -5.0197

Max Act: 3.9196. Min Act: -0.0000

Data Index: 1406871 (The Pile)

Max Activating Token Index: 305

Text #11

Max Range: 5.0197. Min Range: -5.0197

Max Act: 3.8790. Min Act: -0.0000

Data Index: 575584 (The Pile)

Max Activating Token Index: 42

Text #12

Max Range: 5.0197. Min Range: -5.0197

Max Act: 3.8738. Min Act: -0.0000

Data Index: 1205089 (The Pile)

Max Activating Token Index: 223

Text #13

Max Range: 5.0197. Min Range: -5.0197

Max Act: 3.8641. Min Act: -0.0000

Data Index: 172272 (The Pile)

Max Activating Token Index: 96

Text #14

Max Range: 5.0197. Min Range: -5.0197

Max Act: 3.5336. Min Act: -0.0000

Data Index: 579263 (The Pile)

Max Activating Token Index: 61

Text #15

Max Range: 5.0197. Min Range: -5.0197

Max Act: 3.8374. Min Act: -0.0000

Data Index: 1965623 (The Pile)

Max Activating Token Index: 418

Text #16

Max Range: 5.0197. Min Range: -5.0197

Max Act: 3.8359. Min Act: -0.0000

Data Index: 1707762 (The Pile)

Max Activating Token Index: 576

Text #17

Max Range: 5.0197. Min Range: -5.0197

Max Act: 3.9939. Min Act: -0.0000

Data Index: 1408621 (The Pile)

Max Activating Token Index: 314

Text #18

Max Range: 5.0197. Min Range: -5.0197

Max Act: 3.9358. Min Act: -0.0000

Data Index: 1589056 (The Pile)

Max Activating Token Index: 92

Text #19

Max Range: 5.0197. Min Range: -5.0197

Max Act: 3.4542. Min Act: -0.0000

Data Index: 1788286 (The Pile)

Max Activating Token Index: 789