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

Dataset: The Pile

Neuron 3554 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: 3.4974. Min Range: -3.4974

Max Act: 3.4974. Min Act: -0.0000

Data Index: 373932 (The Pile)

Max Activating Token Index: 1011

Text #1

Max Range: 3.4974. Min Range: -3.4974

Max Act: 2.8811. Min Act: -0.0000

Data Index: 1180695 (The Pile)

Max Activating Token Index: 990

Text #2

Max Range: 3.4974. Min Range: -3.4974

Max Act: 2.9641. Min Act: -0.0000

Data Index: 579721 (The Pile)

Max Activating Token Index: 1009

Text #3

Max Range: 3.4974. Min Range: -3.4974

Max Act: 2.4084. Min Act: -0.0000

Data Index: 1671958 (The Pile)

Max Activating Token Index: 838

Text #4

Max Range: 3.4974. Min Range: -3.4974

Max Act: 2.6185. Min Act: -0.0000

Data Index: 208806 (The Pile)

Max Activating Token Index: 673

Text #5

Max Range: 3.4974. Min Range: -3.4974

Max Act: 2.3527. Min Act: -0.0000

Data Index: 1866279 (The Pile)

Max Activating Token Index: 600

Text #6

Max Range: 3.4974. Min Range: -3.4974

Max Act: 2.0575. Min Act: -0.0000

Data Index: 1093824 (The Pile)

Max Activating Token Index: 225

Text #7

Max Range: 3.4974. Min Range: -3.4974

Max Act: 2.4492. Min Act: -0.0000

Data Index: 844857 (The Pile)

Max Activating Token Index: 330

Text #8

Max Range: 3.4974. Min Range: -3.4974

Max Act: 2.1745. Min Act: -0.0000

Data Index: 202285 (The Pile)

Max Activating Token Index: 162

Text #9

Max Range: 3.4974. Min Range: -3.4974

Max Act: 2.1620. Min Act: -0.0000

Data Index: 1315404 (The Pile)

Max Activating Token Index: 197

Text #10

Max Range: 3.4974. Min Range: -3.4974

Max Act: 2.2176. Min Act: -0.0000

Data Index: 137292 (The Pile)

Max Activating Token Index: 200

Text #11

Max Range: 3.4974. Min Range: -3.4974

Max Act: 2.4637. Min Act: -0.0000

Data Index: 104577 (The Pile)

Max Activating Token Index: 150

Text #12

Max Range: 3.4974. Min Range: -3.4974

Max Act: 1.9622. Min Act: -0.0000

Data Index: 1153596 (The Pile)

Max Activating Token Index: 150

Text #13

Max Range: 3.4974. Min Range: -3.4974

Max Act: 2.1599. Min Act: -0.0000

Data Index: 1902530 (The Pile)

Max Activating Token Index: 209

Text #14

Max Range: 3.4974. Min Range: -3.4974

Max Act: 2.1816. Min Act: -0.0000

Data Index: 1913410 (The Pile)

Max Activating Token Index: 176

Text #15

Max Range: 3.4974. Min Range: -3.4974

Max Act: 2.3279. Min Act: -0.0000

Data Index: 1128322 (The Pile)

Max Activating Token Index: 1007

Text #16

Max Range: 3.4974. Min Range: -3.4974

Max Act: 2.0352. Min Act: -0.0000

Data Index: 625393 (The Pile)

Max Activating Token Index: 688

Text #17

Max Range: 3.4974. Min Range: -3.4974

Max Act: 1.7035. Min Act: -0.0000

Data Index: 990329 (The Pile)

Max Activating Token Index: 581

Text #18

Max Range: 3.4974. Min Range: -3.4974

Max Act: 2.2557. Min Act: -0.0000

Data Index: 478919 (The Pile)

Max Activating Token Index: 243

Text #19

Max Range: 3.4974. Min Range: -3.4974

Max Act: 2.1355. Min Act: -0.0000

Data Index: 1949647 (The Pile)

Max Activating Token Index: 175