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

Dataset: The Pile

Neuron 3011 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: 0.0852. Min Range: -0.0852

Max Act: 0.0852. Min Act: -0.0000

Data Index: 162942 (The Pile)

Max Activating Token Index: 524

Text #1

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0681. Min Act: -0.0000

Data Index: 1284161 (The Pile)

Max Activating Token Index: 186

Text #2

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0687. Min Act: -0.0000

Data Index: 1615769 (The Pile)

Max Activating Token Index: 61

Text #3

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0693. Min Act: -0.0000

Data Index: 1063336 (The Pile)

Max Activating Token Index: 57

Text #4

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0673. Min Act: -0.0000

Data Index: 378949 (The Pile)

Max Activating Token Index: 321

Text #5

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0625. Min Act: -0.0000

Data Index: 545910 (The Pile)

Max Activating Token Index: 996

Text #6

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0622. Min Act: -0.0000

Data Index: 665984 (The Pile)

Max Activating Token Index: 37

Text #7

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0645. Min Act: -0.0000

Data Index: 1063448 (The Pile)

Max Activating Token Index: 126

Text #8

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0641. Min Act: -0.0000

Data Index: 999008 (The Pile)

Max Activating Token Index: 80

Text #9

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0629. Min Act: -0.0000

Data Index: 264612 (The Pile)

Max Activating Token Index: 540

Text #10

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0620. Min Act: -0.0000

Data Index: 410049 (The Pile)

Max Activating Token Index: 523

Text #11

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0638. Min Act: -0.0000

Data Index: 1546050 (The Pile)

Max Activating Token Index: 514

Text #12

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0660. Min Act: -0.0000

Data Index: 290240 (The Pile)

Max Activating Token Index: 515

Text #13

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0554. Min Act: -0.0000

Data Index: 1067262 (The Pile)

Max Activating Token Index: 793

Text #14

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0605. Min Act: -0.0000

Data Index: 1533787 (The Pile)

Max Activating Token Index: 180

Text #15

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0643. Min Act: -0.0000

Data Index: 1361303 (The Pile)

Max Activating Token Index: 613

Text #16

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0609. Min Act: -0.0000

Data Index: 335112 (The Pile)

Max Activating Token Index: 240

Text #17

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0551. Min Act: -0.0000

Data Index: 1753135 (The Pile)

Max Activating Token Index: 921

Text #18

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0543. Min Act: -0.0000

Data Index: 500500 (The Pile)

Max Activating Token Index: 763

Text #19

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0551. Min Act: -0.0000

Data Index: 841817 (The Pile)

Max Activating Token Index: 215