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

Dataset: The Pile

Neuron 2658 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: 0.5565. Min Range: -0.5565

Max Act: 0.5425. Min Act: -0.0000

Data Index: 264428 (The Pile)

Max Activating Token Index: 54

Text #1

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.5308. Min Act: -0.0000

Data Index: 178523 (The Pile)

Max Activating Token Index: 703

Text #2

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.5565. Min Act: -0.0000

Data Index: 1659468 (The Pile)

Max Activating Token Index: 164

Text #3

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.5379. Min Act: -0.0000

Data Index: 73665 (The Pile)

Max Activating Token Index: 958

Text #4

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.5474. Min Act: -0.0000

Data Index: 305435 (The Pile)

Max Activating Token Index: 861

Text #5

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.5124. Min Act: -0.0000

Data Index: 1482963 (The Pile)

Max Activating Token Index: 24

Text #6

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.5102. Min Act: -0.0000

Data Index: 1234801 (The Pile)

Max Activating Token Index: 803

Text #7

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1517051 (The Pile)

Max Activating Token Index: 861

Text #8

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4985. Min Act: -0.0000

Data Index: 945080 (The Pile)

Max Activating Token Index: 592

Text #9

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.5080. Min Act: -0.0001

Data Index: 876741 (The Pile)

Max Activating Token Index: 234

Text #10

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.5021. Min Act: -0.0000

Data Index: 673085 (The Pile)

Max Activating Token Index: 154

Text #11

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.5013. Min Act: -0.0000

Data Index: 902747 (The Pile)

Max Activating Token Index: 381

Text #12

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4987. Min Act: -0.0000

Data Index: 133954 (The Pile)

Max Activating Token Index: 157

Text #13

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4964. Min Act: -0.0000

Data Index: 1292430 (The Pile)

Max Activating Token Index: 285

Text #14

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4811. Min Act: -0.0000

Data Index: 1993071 (The Pile)

Max Activating Token Index: 662

Text #15

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1660026 (The Pile)

Max Activating Token Index: 450

Text #16

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1335582 (The Pile)

Max Activating Token Index: 192

Text #17

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.5006. Min Act: -0.0000

Data Index: 357216 (The Pile)

Max Activating Token Index: 695

Text #18

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4725. Min Act: -0.0000

Data Index: 722125 (The Pile)

Max Activating Token Index: 727

Text #19

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.5083. Min Act: -0.0000

Data Index: 1430132 (The Pile)

Max Activating Token Index: 920