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

Dataset: The Pile

Neuron 2116 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: 0.6120. Min Range: -0.6120

Max Act: 0.6120. Min Act: -0.0000

Data Index: 1323173 (The Pile)

Max Activating Token Index: 632

Text #1

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.5492. Min Act: -0.0000

Data Index: 983562 (The Pile)

Max Activating Token Index: 591

Text #2

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1489037 (The Pile)

Max Activating Token Index: 969

Text #3

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4712. Min Act: -0.0000

Data Index: 207915 (The Pile)

Max Activating Token Index: 467

Text #4

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4750. Min Act: -0.0000

Data Index: 561683 (The Pile)

Max Activating Token Index: 380

Text #5

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1847314 (The Pile)

Max Activating Token Index: 290

Text #6

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4463. Min Act: -0.0000

Data Index: 1639217 (The Pile)

Max Activating Token Index: 576

Text #7

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4188. Min Act: -0.0000

Data Index: 169704 (The Pile)

Max Activating Token Index: 281

Text #8

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4064. Min Act: -0.0000

Data Index: 602492 (The Pile)

Max Activating Token Index: 747

Text #9

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.3931. Min Act: -0.0000

Data Index: 900206 (The Pile)

Max Activating Token Index: 337

Text #10

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4041. Min Act: -0.0000

Data Index: 826941 (The Pile)

Max Activating Token Index: 611

Text #11

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1578765 (The Pile)

Max Activating Token Index: 305

Text #12

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4004. Min Act: -0.0000

Data Index: 1213155 (The Pile)

Max Activating Token Index: 397

Text #13

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.3992. Min Act: -0.0000

Data Index: 1938368 (The Pile)

Max Activating Token Index: 16

Text #14

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.3811. Min Act: -0.0000

Data Index: 230849 (The Pile)

Max Activating Token Index: 202

Text #15

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.3456. Min Act: -0.0000

Data Index: 1445153 (The Pile)

Max Activating Token Index: 826

Text #16

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.3918. Min Act: -0.0000

Data Index: 16965 (The Pile)

Max Activating Token Index: 710

Text #17

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.3699. Min Act: -0.0000

Data Index: 1977497 (The Pile)

Max Activating Token Index: 769

Text #18

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.3613. Min Act: -0.0000

Data Index: 1381181 (The Pile)

Max Activating Token Index: 672

Text #19

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.3562. Min Act: -0.0000

Data Index: 343267 (The Pile)

Max Activating Token Index: 829