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

Dataset: The Pile

Neuron 748 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: 0.8783. Min Range: -0.8783

Max Act: 0.8783. Min Act: -0.0000

Data Index: 1007357 (The Pile)

Max Activating Token Index: 33

Text #1

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.7260. Min Act: -0.0000

Data Index: 441541 (The Pile)

Max Activating Token Index: 22

Text #2

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6655. Min Act: -0.0000

Data Index: 484801 (The Pile)

Max Activating Token Index: 530

Text #3

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.7768. Min Act: -0.0000

Data Index: 1762200 (The Pile)

Max Activating Token Index: 16

Text #4

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.7536. Min Act: -0.0000

Data Index: 1052034 (The Pile)

Max Activating Token Index: 67

Text #5

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6893. Min Act: -0.0000

Data Index: 1633744 (The Pile)

Max Activating Token Index: 54

Text #6

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.7000. Min Act: -0.0000

Data Index: 1177661 (The Pile)

Max Activating Token Index: 119

Text #7

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1989657 (The Pile)

Max Activating Token Index: 523

Text #8

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1547610 (The Pile)

Max Activating Token Index: 451

Text #9

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6405. Min Act: -0.0000

Data Index: 349431 (The Pile)

Max Activating Token Index: 297

Text #10

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6459. Min Act: -0.0000

Data Index: 971145 (The Pile)

Max Activating Token Index: 655

Text #11

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6423. Min Act: -0.0000

Data Index: 292245 (The Pile)

Max Activating Token Index: 146

Text #12

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6405. Min Act: -0.0000

Data Index: 1799201 (The Pile)

Max Activating Token Index: 173

Text #13

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6612. Min Act: -0.0000

Data Index: 717188 (The Pile)

Max Activating Token Index: 25

Text #14

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6554. Min Act: -0.0000

Data Index: 134087 (The Pile)

Max Activating Token Index: 649

Text #15

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6760. Min Act: -0.0000

Data Index: 1311576 (The Pile)

Max Activating Token Index: 214

Text #16

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6080. Min Act: -0.0000

Data Index: 1043316 (The Pile)

Max Activating Token Index: 451

Text #17

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6034. Min Act: -0.0000

Data Index: 1804176 (The Pile)

Max Activating Token Index: 329

Text #18

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.5854. Min Act: -0.0000

Data Index: 474009 (The Pile)

Max Activating Token Index: 91

Text #19

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.5999. Min Act: -0.0000

Data Index: 1191085 (The Pile)

Max Activating Token Index: 162