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

Dataset: The Pile

Neuron 4552 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.9207. Min Act: -0.0000

Data Index: 387246 (The Pile)

Max Activating Token Index: 959

Text #1

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1306760 (The Pile)

Max Activating Token Index: 355

Text #2

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.9274. Min Act: -0.0000

Data Index: 678047 (The Pile)

Max Activating Token Index: 235

Text #3

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.9313. Min Act: -0.0000

Data Index: 1712576 (The Pile)

Max Activating Token Index: 436

Text #4

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8979. Min Act: -0.0000

Data Index: 882101 (The Pile)

Max Activating Token Index: 246

Text #5

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.9449. Min Act: -0.0000

Data Index: 1930855 (The Pile)

Max Activating Token Index: 879

Text #6

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8614. Min Act: -0.0000

Data Index: 118580 (The Pile)

Max Activating Token Index: 328

Text #7

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8178. Min Act: -0.0000

Data Index: 1095241 (The Pile)

Max Activating Token Index: 247

Text #8

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8146. Min Act: -0.0000

Data Index: 738098 (The Pile)

Max Activating Token Index: 838

Text #9

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8182. Min Act: -0.0000

Data Index: 414146 (The Pile)

Max Activating Token Index: 35

Text #10

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8121. Min Act: -0.0000

Data Index: 170770 (The Pile)

Max Activating Token Index: 664

Text #11

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8095. Min Act: -0.0000

Data Index: 1642063 (The Pile)

Max Activating Token Index: 419

Text #12

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.7806. Min Act: -0.0000

Data Index: 637613 (The Pile)

Max Activating Token Index: 840

Text #13

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.7806. Min Act: -0.0000

Data Index: 1687343 (The Pile)

Max Activating Token Index: 436

Text #14

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.7962. Min Act: -0.0000

Data Index: 1417261 (The Pile)

Max Activating Token Index: 655

Text #15

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.7503. Min Act: -0.0000

Data Index: 569682 (The Pile)

Max Activating Token Index: 618

Text #16

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.7596. Min Act: -0.0000

Data Index: 1064923 (The Pile)

Max Activating Token Index: 988

Text #17

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1474087 (The Pile)

Max Activating Token Index: 412

Text #18

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1242051 (The Pile)

Max Activating Token Index: 163

Text #19

Max Range: 0.9449. Min Range: -0.9449

Max Act: 0.7782. Min Act: -0.0000

Data Index: 1920830 (The Pile)

Max Activating Token Index: 771