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

Dataset: The Pile

Neuron 3668 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: 0.6193. Min Range: -0.6193

Max Act: 0.6193. Min Act: -0.0000

Data Index: 544610 (The Pile)

Max Activating Token Index: 100

Text #1

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.6090. Min Act: -0.0000

Data Index: 403841 (The Pile)

Max Activating Token Index: 212

Text #2

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5581. Min Act: 0.0000

Data Index: 1292649 (The Pile)

Max Activating Token Index: 6

Text #3

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5571. Min Act: -0.0000

Data Index: 1861178 (The Pile)

Max Activating Token Index: 372

Text #4

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5893. Min Act: -0.0000

Data Index: 776897 (The Pile)

Max Activating Token Index: 945

Text #5

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5950. Min Act: 0.0000

Data Index: 1565864 (The Pile)

Max Activating Token Index: 373

Text #6

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1139829 (The Pile)

Max Activating Token Index: 569

Text #7

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5589. Min Act: -0.0000

Data Index: 1477218 (The Pile)

Max Activating Token Index: 287

Text #8

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5069. Min Act: -0.0000

Data Index: 234238 (The Pile)

Max Activating Token Index: 292

Text #9

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5645. Min Act: -0.0000

Data Index: 485126 (The Pile)

Max Activating Token Index: 746

Text #10

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4943. Min Act: -0.0000

Data Index: 1516256 (The Pile)

Max Activating Token Index: 113

Text #11

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4684. Min Act: 0.0000

Data Index: 124596 (The Pile)

Max Activating Token Index: 221

Text #12

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5128. Min Act: -0.0000

Data Index: 1132695 (The Pile)

Max Activating Token Index: 29

Text #13

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5108. Min Act: -0.0000

Data Index: 281531 (The Pile)

Max Activating Token Index: 848

Text #14

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4937. Min Act: -0.0000

Data Index: 1929518 (The Pile)

Max Activating Token Index: 644

Text #15

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4934. Min Act: -0.0000

Data Index: 1863958 (The Pile)

Max Activating Token Index: 194

Text #16

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4770. Min Act: -0.0000

Data Index: 818910 (The Pile)

Max Activating Token Index: 742

Text #17

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4607. Min Act: -0.0000

Data Index: 125537 (The Pile)

Max Activating Token Index: 10

Text #18

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4868. Min Act: -0.0000

Data Index: 299086 (The Pile)

Max Activating Token Index: 479

Text #19

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1245240 (The Pile)

Max Activating Token Index: 461