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

Dataset: The Pile

Neuron 716 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: 0.9681. Min Range: -0.9681

Max Act: 0.9681. Min Act: -0.0000

Data Index: 955092 (The Pile)

Max Activating Token Index: 230

Text #1

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.9216. Min Act: -0.0000

Data Index: 1924167 (The Pile)

Max Activating Token Index: 201

Text #2

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.9627. Min Act: -0.0000

Data Index: 626121 (The Pile)

Max Activating Token Index: 251

Text #3

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.8658. Min Act: -0.0000

Data Index: 629069 (The Pile)

Max Activating Token Index: 142

Text #4

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.9140. Min Act: -0.0000

Data Index: 1598238 (The Pile)

Max Activating Token Index: 356

Text #5

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.8410. Min Act: -0.0000

Data Index: 1868135 (The Pile)

Max Activating Token Index: 381

Text #6

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.8449. Min Act: -0.0000

Data Index: 1843404 (The Pile)

Max Activating Token Index: 488

Text #7

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.8163. Min Act: -0.0000

Data Index: 776982 (The Pile)

Max Activating Token Index: 114

Text #8

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.7783. Min Act: -0.0000

Data Index: 1839176 (The Pile)

Max Activating Token Index: 207

Text #9

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.8001. Min Act: -0.0000

Data Index: 184855 (The Pile)

Max Activating Token Index: 292

Text #10

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.8532. Min Act: -0.0000

Data Index: 1129429 (The Pile)

Max Activating Token Index: 346

Text #11

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.8159. Min Act: -0.0000

Data Index: 1892589 (The Pile)

Max Activating Token Index: 531

Text #12

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.7866. Min Act: -0.0000

Data Index: 829380 (The Pile)

Max Activating Token Index: 81

Text #13

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.9068. Min Act: -0.0000

Data Index: 968024 (The Pile)

Max Activating Token Index: 110

Text #14

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.7976. Min Act: -0.0000

Data Index: 1725912 (The Pile)

Max Activating Token Index: 109

Text #15

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.8429. Min Act: -0.0000

Data Index: 205905 (The Pile)

Max Activating Token Index: 432

Text #16

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.8229. Min Act: -0.0000

Data Index: 545209 (The Pile)

Max Activating Token Index: 48

Text #17

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.7639. Min Act: -0.0000

Data Index: 721740 (The Pile)

Max Activating Token Index: 754

Text #18

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.7928. Min Act: -0.0000

Data Index: 1025055 (The Pile)

Max Activating Token Index: 730

Text #19

Max Range: 0.9681. Min Range: -0.9681

Max Act: 0.7482. Min Act: -0.0000

Data Index: 1688321 (The Pile)

Max Activating Token Index: 878