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

Dataset: The Pile

Neuron 1829 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.8810. Min Act: -0.0000

Data Index: 1195287 (The Pile)

Max Activating Token Index: 472

Text #1

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.7403. Min Act: -0.0000

Data Index: 622837 (The Pile)

Max Activating Token Index: 654

Text #2

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.8401. Min Act: -0.0000

Data Index: 657969 (The Pile)

Max Activating Token Index: 126

Text #3

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.7602. Min Act: -0.0000

Data Index: 1928112 (The Pile)

Max Activating Token Index: 648

Text #4

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.8114. Min Act: -0.0000

Data Index: 690996 (The Pile)

Max Activating Token Index: 956

Text #5

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.7526. Min Act: -0.0000

Data Index: 1579144 (The Pile)

Max Activating Token Index: 100

Text #6

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.8100. Min Act: -0.0000

Data Index: 1525764 (The Pile)

Max Activating Token Index: 275

Text #7

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.8075. Min Act: -0.0000

Data Index: 372146 (The Pile)

Max Activating Token Index: 210

Text #8

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.6970. Min Act: -0.0000

Data Index: 114111 (The Pile)

Max Activating Token Index: 46

Text #9

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.7092. Min Act: -0.0000

Data Index: 973687 (The Pile)

Max Activating Token Index: 293

Text #10

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.7507. Min Act: -0.0000

Data Index: 1065825 (The Pile)

Max Activating Token Index: 76

Text #11

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.8111. Min Act: -0.0000

Data Index: 400746 (The Pile)

Max Activating Token Index: 441

Text #12

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.7252. Min Act: -0.0000

Data Index: 133402 (The Pile)

Max Activating Token Index: 27

Text #13

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.7169. Min Act: -0.0000

Data Index: 1552624 (The Pile)

Max Activating Token Index: 180

Text #14

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.7086. Min Act: -0.0000

Data Index: 583545 (The Pile)

Max Activating Token Index: 225

Text #15

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.6771. Min Act: -0.0000

Data Index: 1853684 (The Pile)

Max Activating Token Index: 517

Text #16

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1827516 (The Pile)

Max Activating Token Index: 550

Text #17

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.6135. Min Act: -0.0000

Data Index: 1468310 (The Pile)

Max Activating Token Index: 871

Text #18

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.6748. Min Act: -0.0000

Data Index: 342395 (The Pile)

Max Activating Token Index: 62

Text #19

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.6739. Min Act: -0.0000

Data Index: 1337064 (The Pile)

Max Activating Token Index: 285