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

Dataset: The Pile

Neuron 541 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.4644. Min Act: -0.0000

Data Index: 426354 (The Pile)

Max Activating Token Index: 362

Text #1

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.4503. Min Act: -0.0000

Data Index: 1283301 (The Pile)

Max Activating Token Index: 540

Text #2

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1002147 (The Pile)

Max Activating Token Index: 41

Text #3

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3652. Min Act: -0.0000

Data Index: 1620800 (The Pile)

Max Activating Token Index: 589

Text #4

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3332. Min Act: -0.0000

Data Index: 1347617 (The Pile)

Max Activating Token Index: 51

Text #5

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3661. Min Act: -0.0000

Data Index: 1156047 (The Pile)

Max Activating Token Index: 567

Text #6

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3536. Min Act: -0.0000

Data Index: 1636755 (The Pile)

Max Activating Token Index: 502

Text #7

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3481. Min Act: -0.0000

Data Index: 1613522 (The Pile)

Max Activating Token Index: 348

Text #8

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3410. Min Act: -0.0000

Data Index: 1246632 (The Pile)

Max Activating Token Index: 950

Text #9

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3297. Min Act: -0.0000

Data Index: 1424547 (The Pile)

Max Activating Token Index: 58

Text #10

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3400. Min Act: -0.0000

Data Index: 132603 (The Pile)

Max Activating Token Index: 512

Text #11

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3418. Min Act: -0.0000

Data Index: 781937 (The Pile)

Max Activating Token Index: 182

Text #12

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3531. Min Act: -0.0000

Data Index: 942119 (The Pile)

Max Activating Token Index: 463

Text #13

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3255. Min Act: -0.0000

Data Index: 896505 (The Pile)

Max Activating Token Index: 500

Text #14

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3206. Min Act: -0.0000

Data Index: 156706 (The Pile)

Max Activating Token Index: 149

Text #15

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1975926 (The Pile)

Max Activating Token Index: 28

Text #16

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3177. Min Act: -0.0000

Data Index: 211316 (The Pile)

Max Activating Token Index: 352

Text #17

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.2977. Min Act: -0.0000

Data Index: 1435688 (The Pile)

Max Activating Token Index: 925

Text #18

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3143. Min Act: -0.0000

Data Index: 6422 (The Pile)

Max Activating Token Index: 132

Text #19

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.2881. Min Act: -0.0000

Data Index: 1503918 (The Pile)

Max Activating Token Index: 276