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

Dataset: The Pile

Neuron 1260 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0853. Min Range: -1.0853

Max Act: 1.0794. Min Act: -0.0000

Data Index: 489125 (The Pile)

Max Activating Token Index: 373

Text #1

Max Range: 1.0853. Min Range: -1.0853

Max Act: 1.0192. Min Act: -0.0000

Data Index: 1298878 (The Pile)

Max Activating Token Index: 470

Text #2

Max Range: 1.0853. Min Range: -1.0853

Max Act: 1.0853. Min Act: -0.0000

Data Index: 1146054 (The Pile)

Max Activating Token Index: 277

Text #3

Max Range: 1.0853. Min Range: -1.0853

Max Act: 1.0553. Min Act: -0.0000

Data Index: 313152 (The Pile)

Max Activating Token Index: 40

Text #4

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.9220. Min Act: -0.0000

Data Index: 329093 (The Pile)

Max Activating Token Index: 48

Text #5

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.9319. Min Act: -0.0000

Data Index: 1072345 (The Pile)

Max Activating Token Index: 197

Text #6

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.9630. Min Act: -0.0000

Data Index: 1960149 (The Pile)

Max Activating Token Index: 769

Text #7

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.8828. Min Act: -0.0000

Data Index: 1210887 (The Pile)

Max Activating Token Index: 528

Text #8

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.7730. Min Act: -0.0000

Data Index: 756874 (The Pile)

Max Activating Token Index: 523

Text #9

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.7848. Min Act: -0.0000

Data Index: 568076 (The Pile)

Max Activating Token Index: 585

Text #10

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.8139. Min Act: -0.0000

Data Index: 1158884 (The Pile)

Max Activating Token Index: 54

Text #11

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.8344. Min Act: -0.0000

Data Index: 1950563 (The Pile)

Max Activating Token Index: 743

Text #12

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.8387. Min Act: -0.0000

Data Index: 1968198 (The Pile)

Max Activating Token Index: 345

Text #13

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.8091. Min Act: -0.0001

Data Index: 1153216 (The Pile)

Max Activating Token Index: 24

Text #14

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.7764. Min Act: -0.0000

Data Index: 1540553 (The Pile)

Max Activating Token Index: 64

Text #15

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.8310. Min Act: -0.0000

Data Index: 1849757 (The Pile)

Max Activating Token Index: 127

Text #16

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.8570. Min Act: 0.0000

Data Index: 1379371 (The Pile)

Max Activating Token Index: 73

Text #17

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.8078. Min Act: -0.0000

Data Index: 292439 (The Pile)

Max Activating Token Index: 67

Text #18

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.7926. Min Act: -0.0000

Data Index: 242837 (The Pile)

Max Activating Token Index: 835

Text #19

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.7851. Min Act: -0.0000

Data Index: 1844422 (The Pile)

Max Activating Token Index: 669