Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3915 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.3075. Min Act: -0.0000

Data Index: 1939715 (The Pile)

Max Activating Token Index: 140

Text #1

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.2808. Min Act: -0.0000

Data Index: 1986390 (The Pile)

Max Activating Token Index: 170

Text #2

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.2118. Min Act: -0.0000

Data Index: 1650051 (The Pile)

Max Activating Token Index: 329

Text #3

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.1617. Min Act: -0.0000

Data Index: 442218 (The Pile)

Max Activating Token Index: 117

Text #4

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.1549. Min Act: -0.0000

Data Index: 1360318 (The Pile)

Max Activating Token Index: 957

Text #5

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.0901. Min Act: -0.0000

Data Index: 401610 (The Pile)

Max Activating Token Index: 206

Text #6

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.0269. Min Act: -0.0000

Data Index: 1811666 (The Pile)

Max Activating Token Index: 62

Text #7

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.0155. Min Act: -0.0000

Data Index: 1657438 (The Pile)

Max Activating Token Index: 156

Text #8

Max Range: 1.3075. Min Range: -1.3075

Max Act: 0.9668. Min Act: -0.0000

Data Index: 400877 (The Pile)

Max Activating Token Index: 182

Text #9

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.0286. Min Act: -0.0000

Data Index: 1722156 (The Pile)

Max Activating Token Index: 985

Text #10

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.0107. Min Act: -0.0000

Data Index: 197393 (The Pile)

Max Activating Token Index: 298

Text #11

Max Range: 1.3075. Min Range: -1.3075

Max Act: 0.9819. Min Act: -0.0000

Data Index: 952699 (The Pile)

Max Activating Token Index: 220

Text #12

Max Range: 1.3075. Min Range: -1.3075

Max Act: 0.9412. Min Act: -0.0000

Data Index: 754272 (The Pile)

Max Activating Token Index: 273

Text #13

Max Range: 1.3075. Min Range: -1.3075

Max Act: 0.9931. Min Act: -0.0000

Data Index: 351422 (The Pile)

Max Activating Token Index: 316

Text #14

Max Range: 1.3075. Min Range: -1.3075

Max Act: 0.9788. Min Act: -0.0000

Data Index: 804803 (The Pile)

Max Activating Token Index: 381

Text #15

Max Range: 1.3075. Min Range: -1.3075

Max Act: 0.9627. Min Act: -0.0000

Data Index: 1393528 (The Pile)

Max Activating Token Index: 149

Text #16

Max Range: 1.3075. Min Range: -1.3075

Max Act: 0.9269. Min Act: -0.0000

Data Index: 619902 (The Pile)

Max Activating Token Index: 347

Text #17

Max Range: 1.3075. Min Range: -1.3075

Max Act: 0.9549. Min Act: -0.0000

Data Index: 560953 (The Pile)

Max Activating Token Index: 355

Text #18

Max Range: 1.3075. Min Range: -1.3075

Max Act: 0.9506. Min Act: -0.0000

Data Index: 300790 (The Pile)

Max Activating Token Index: 33

Text #19

Max Range: 1.3075. Min Range: -1.3075

Max Act: 0.8846. Min Act: -0.0000

Data Index: 207792 (The Pile)

Max Activating Token Index: 143