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

Dataset: The Pile

Neuron 2056 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.9261. Min Act: -0.0000

Data Index: 1571737 (The Pile)

Max Activating Token Index: 280

Text #1

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.9094. Min Act: -0.0000

Data Index: 831501 (The Pile)

Max Activating Token Index: 867

Text #2

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7780. Min Act: -0.0000

Data Index: 1494965 (The Pile)

Max Activating Token Index: 99

Text #3

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1827774 (The Pile)

Max Activating Token Index: 376

Text #4

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7808. Min Act: -0.0000

Data Index: 1511208 (The Pile)

Max Activating Token Index: 474

Text #5

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7627. Min Act: -0.0000

Data Index: 1155007 (The Pile)

Max Activating Token Index: 274

Text #6

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7329. Min Act: -0.0000

Data Index: 1901870 (The Pile)

Max Activating Token Index: 953

Text #7

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6672. Min Act: -0.0000

Data Index: 1274052 (The Pile)

Max Activating Token Index: 601

Text #8

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7490. Min Act: -0.0000

Data Index: 1060231 (The Pile)

Max Activating Token Index: 323

Text #9

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6926. Min Act: -0.0000

Data Index: 1506304 (The Pile)

Max Activating Token Index: 851

Text #10

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6836. Min Act: -0.0000

Data Index: 901068 (The Pile)

Max Activating Token Index: 44

Text #11

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7200. Min Act: -0.0000

Data Index: 1342609 (The Pile)

Max Activating Token Index: 918

Text #12

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6734. Min Act: -0.0000

Data Index: 1184836 (The Pile)

Max Activating Token Index: 577

Text #13

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6745. Min Act: -0.0000

Data Index: 1324001 (The Pile)

Max Activating Token Index: 954

Text #14

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6953. Min Act: -0.0000

Data Index: 1616168 (The Pile)

Max Activating Token Index: 383

Text #15

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6579. Min Act: -0.0000

Data Index: 632443 (The Pile)

Max Activating Token Index: 846

Text #16

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6093. Min Act: -0.0000

Data Index: 294919 (The Pile)

Max Activating Token Index: 56

Text #17

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6160. Min Act: -0.0000

Data Index: 1527451 (The Pile)

Max Activating Token Index: 810

Text #18

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6349. Min Act: -0.0000

Data Index: 798609 (The Pile)

Max Activating Token Index: 209

Text #19

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6354. Min Act: -0.0000

Data Index: 700425 (The Pile)

Max Activating Token Index: 664