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

Dataset: The Pile

Neuron 4317 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: 0.8913. Min Range: -0.8913

Max Act: 0.8913. Min Act: 0.0000

Data Index: 1045443 (The Pile)

Max Activating Token Index: 119

Text #1

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7446. Min Act: -0.0000

Data Index: 615491 (The Pile)

Max Activating Token Index: 36

Text #2

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7113. Min Act: -0.0000

Data Index: 522881 (The Pile)

Max Activating Token Index: 350

Text #3

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1634066 (The Pile)

Max Activating Token Index: 873

Text #4

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.6722. Min Act: -0.0000

Data Index: 348933 (The Pile)

Max Activating Token Index: 158

Text #5

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.6980. Min Act: -0.0000

Data Index: 442743 (The Pile)

Max Activating Token Index: 387

Text #6

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7129. Min Act: -0.0000

Data Index: 776104 (The Pile)

Max Activating Token Index: 904

Text #7

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.6985. Min Act: -0.0000

Data Index: 844163 (The Pile)

Max Activating Token Index: 11

Text #8

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1270163 (The Pile)

Max Activating Token Index: 629

Text #9

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.6410. Min Act: -0.0000

Data Index: 902937 (The Pile)

Max Activating Token Index: 186

Text #10

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.6604. Min Act: -0.0000

Data Index: 681024 (The Pile)

Max Activating Token Index: 273

Text #11

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.6999. Min Act: -0.0000

Data Index: 1430781 (The Pile)

Max Activating Token Index: 899

Text #12

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.6584. Min Act: -0.0000

Data Index: 950235 (The Pile)

Max Activating Token Index: 115

Text #13

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.6700. Min Act: -0.0000

Data Index: 942135 (The Pile)

Max Activating Token Index: 67

Text #14

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.6543. Min Act: -0.0000

Data Index: 1763114 (The Pile)

Max Activating Token Index: 478

Text #15

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.6662. Min Act: -0.0000

Data Index: 227783 (The Pile)

Max Activating Token Index: 140

Text #16

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.6398. Min Act: 0.0000

Data Index: 1392117 (The Pile)

Max Activating Token Index: 146

Text #17

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.6740. Min Act: -0.0000

Data Index: 260688 (The Pile)

Max Activating Token Index: 196

Text #18

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.6486. Min Act: -0.0000

Data Index: 660137 (The Pile)

Max Activating Token Index: 557

Text #19

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.6269. Min Act: -0.0000

Data Index: 313088 (The Pile)

Max Activating Token Index: 34