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

Dataset: The Pile

Neuron 2966 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: 0.8981. Min Range: -0.8981

Max Act: 0.8905. Min Act: -0.0000

Data Index: 1026521 (The Pile)

Max Activating Token Index: 711

Text #1

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8281. Min Act: -0.0000

Data Index: 1097934 (The Pile)

Max Activating Token Index: 845

Text #2

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8981. Min Act: -0.0000

Data Index: 533209 (The Pile)

Max Activating Token Index: 821

Text #3

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8797. Min Act: -0.0000

Data Index: 8909 (The Pile)

Max Activating Token Index: 651

Text #4

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8759. Min Act: -0.0000

Data Index: 1343421 (The Pile)

Max Activating Token Index: 205

Text #5

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7702. Min Act: -0.0000

Data Index: 1810810 (The Pile)

Max Activating Token Index: 297

Text #6

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7545. Min Act: -0.0000

Data Index: 610019 (The Pile)

Max Activating Token Index: 306

Text #7

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7502. Min Act: -0.0000

Data Index: 405428 (The Pile)

Max Activating Token Index: 377

Text #8

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6492. Min Act: -0.0000

Data Index: 1619220 (The Pile)

Max Activating Token Index: 311

Text #9

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7790. Min Act: -0.0000

Data Index: 1002709 (The Pile)

Max Activating Token Index: 531

Text #10

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7250. Min Act: -0.0000

Data Index: 1146136 (The Pile)

Max Activating Token Index: 504

Text #11

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6515. Min Act: -0.0000

Data Index: 335027 (The Pile)

Max Activating Token Index: 200

Text #12

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6834. Min Act: -0.0000

Data Index: 413057 (The Pile)

Max Activating Token Index: 1017

Text #13

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1771153 (The Pile)

Max Activating Token Index: 479

Text #14

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6467. Min Act: -0.0000

Data Index: 243385 (The Pile)

Max Activating Token Index: 592

Text #15

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7347. Min Act: -0.0000

Data Index: 895878 (The Pile)

Max Activating Token Index: 394

Text #16

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6810. Min Act: -0.0000

Data Index: 200551 (The Pile)

Max Activating Token Index: 125

Text #17

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7560. Min Act: -0.0000

Data Index: 1599057 (The Pile)

Max Activating Token Index: 734

Text #18

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1931127 (The Pile)

Max Activating Token Index: 247

Text #19

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8034. Min Act: -0.0000

Data Index: 22119 (The Pile)

Max Activating Token Index: 744