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

Dataset: The Pile

Neuron 1736 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.7019. Min Act: 0.0000

Data Index: 1634833 (The Pile)

Max Activating Token Index: 229

Text #1

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.2480. Min Act: -0.0000

Data Index: 276921 (The Pile)

Max Activating Token Index: 238

Text #2

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.1193. Min Act: -0.0000

Data Index: 99651 (The Pile)

Max Activating Token Index: 919

Text #3

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.1597. Min Act: 0.0000

Data Index: 1186523 (The Pile)

Max Activating Token Index: 123

Text #4

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.2151. Min Act: -0.0000

Data Index: 554499 (The Pile)

Max Activating Token Index: 834

Text #5

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.1974. Min Act: -0.0000

Data Index: 1296296 (The Pile)

Max Activating Token Index: 60

Text #6

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.0328. Min Act: -0.0000

Data Index: 1458682 (The Pile)

Max Activating Token Index: 1008

Text #7

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.0962. Min Act: -0.0000

Data Index: 1978451 (The Pile)

Max Activating Token Index: 11

Text #8

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.2309. Min Act: -0.0000

Data Index: 737638 (The Pile)

Max Activating Token Index: 977

Text #9

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.1555. Min Act: -0.0000

Data Index: 618805 (The Pile)

Max Activating Token Index: 740

Text #10

Max Range: 1.7019. Min Range: -1.7019

Max Act: 0.9783. Min Act: -0.0000

Data Index: 1375947 (The Pile)

Max Activating Token Index: 216

Text #11

Max Range: 1.7019. Min Range: -1.7019

Max Act: 0.9784. Min Act: 0.0000

Data Index: 1435166 (The Pile)

Max Activating Token Index: 18

Text #12

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.0469. Min Act: -0.0000

Data Index: 1830351 (The Pile)

Max Activating Token Index: 103

Text #13

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.0817. Min Act: -0.0000

Data Index: 587302 (The Pile)

Max Activating Token Index: 301

Text #14

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.0131. Min Act: -0.0000

Data Index: 787609 (The Pile)

Max Activating Token Index: 727

Text #15

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.0268. Min Act: 0.0000

Data Index: 684791 (The Pile)

Max Activating Token Index: 1014

Text #16

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.0140. Min Act: -0.0000

Data Index: 1199981 (The Pile)

Max Activating Token Index: 93

Text #17

Max Range: 1.7019. Min Range: -1.7019

Max Act: 0.9639. Min Act: -0.0000

Data Index: 147267 (The Pile)

Max Activating Token Index: 249

Text #18

Max Range: 1.7019. Min Range: -1.7019

Max Act: 1.0214. Min Act: -0.0000

Data Index: 1070892 (The Pile)

Max Activating Token Index: 744

Text #19

Max Range: 1.7019. Min Range: -1.7019

Max Act: 0.9737. Min Act: -0.0000

Data Index: 60643 (The Pile)

Max Activating Token Index: 1010