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

Dataset: The Pile

Neuron 863 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: 1.1763. Min Range: -1.1763

Max Act: 1.1763. Min Act: -0.0000

Data Index: 653607 (The Pile)

Max Activating Token Index: 516

Text #1

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.1550. Min Act: -0.0000

Data Index: 441332 (The Pile)

Max Activating Token Index: 183

Text #2

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.0378. Min Act: -0.0000

Data Index: 1212870 (The Pile)

Max Activating Token Index: 888

Text #3

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.0447. Min Act: -0.0000

Data Index: 526113 (The Pile)

Max Activating Token Index: 922

Text #4

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.9661. Min Act: -0.0000

Data Index: 880349 (The Pile)

Max Activating Token Index: 789

Text #5

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.9299. Min Act: -0.0000

Data Index: 1363758 (The Pile)

Max Activating Token Index: 879

Text #6

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.9065. Min Act: -0.0000

Data Index: 1836149 (The Pile)

Max Activating Token Index: 692

Text #7

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.8697. Min Act: -0.0000

Data Index: 1666833 (The Pile)

Max Activating Token Index: 431

Text #8

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1516086 (The Pile)

Max Activating Token Index: 443

Text #9

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.9134. Min Act: -0.0000

Data Index: 1763096 (The Pile)

Max Activating Token Index: 584

Text #10

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.8731. Min Act: -0.0000

Data Index: 1227293 (The Pile)

Max Activating Token Index: 712

Text #11

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.8753. Min Act: -0.0000

Data Index: 1529417 (The Pile)

Max Activating Token Index: 853

Text #12

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.8438. Min Act: -0.0000

Data Index: 576864 (The Pile)

Max Activating Token Index: 657

Text #13

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.8784. Min Act: -0.0000

Data Index: 888890 (The Pile)

Max Activating Token Index: 754

Text #14

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.8490. Min Act: -0.0000

Data Index: 357573 (The Pile)

Max Activating Token Index: 99

Text #15

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.8172. Min Act: -0.0000

Data Index: 1219242 (The Pile)

Max Activating Token Index: 998

Text #16

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.8379. Min Act: -0.0000

Data Index: 118883 (The Pile)

Max Activating Token Index: 781

Text #17

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.8343. Min Act: -0.0000

Data Index: 1069909 (The Pile)

Max Activating Token Index: 602

Text #18

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.8644. Min Act: -0.0000

Data Index: 1258832 (The Pile)

Max Activating Token Index: 854

Text #19

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.8509. Min Act: -0.0000

Data Index: 1815385 (The Pile)

Max Activating Token Index: 306