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

Dataset: The Pile

Neuron 4287 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3903. Min Range: -1.3903

Max Act: 1.3903. Min Act: -0.0000

Data Index: 742732 (The Pile)

Max Activating Token Index: 417

Text #1

Max Range: 1.3903. Min Range: -1.3903

Max Act: 1.1653. Min Act: -0.0000

Data Index: 1835584 (The Pile)

Max Activating Token Index: 685

Text #2

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.9987. Min Act: -0.0000

Data Index: 424297 (The Pile)

Max Activating Token Index: 240

Text #3

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.9439. Min Act: -0.0000

Data Index: 1972984 (The Pile)

Max Activating Token Index: 1001

Text #4

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.8131. Min Act: -0.0000

Data Index: 3045 (The Pile)

Max Activating Token Index: 1012

Text #5

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.9365. Min Act: -0.0000

Data Index: 1347983 (The Pile)

Max Activating Token Index: 941

Text #6

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.8527. Min Act: -0.0000

Data Index: 1696387 (The Pile)

Max Activating Token Index: 973

Text #7

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.9537. Min Act: -0.0000

Data Index: 1976319 (The Pile)

Max Activating Token Index: 767

Text #8

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.9336. Min Act: -0.0000

Data Index: 158914 (The Pile)

Max Activating Token Index: 954

Text #9

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.8733. Min Act: -0.0000

Data Index: 1859453 (The Pile)

Max Activating Token Index: 464

Text #10

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.9526. Min Act: -0.0000

Data Index: 69313 (The Pile)

Max Activating Token Index: 670

Text #11

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.8528. Min Act: -0.0000

Data Index: 1314560 (The Pile)

Max Activating Token Index: 855

Text #12

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.8161. Min Act: -0.0000

Data Index: 1216514 (The Pile)

Max Activating Token Index: 383

Text #13

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.8314. Min Act: -0.0000

Data Index: 570804 (The Pile)

Max Activating Token Index: 342

Text #14

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.8037. Min Act: -0.0000

Data Index: 445281 (The Pile)

Max Activating Token Index: 447

Text #15

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.7126. Min Act: -0.0000

Data Index: 294517 (The Pile)

Max Activating Token Index: 90

Text #16

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.7758. Min Act: -0.0000

Data Index: 1986760 (The Pile)

Max Activating Token Index: 574

Text #17

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.7350. Min Act: -0.0000

Data Index: 1451059 (The Pile)

Max Activating Token Index: 411

Text #18

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.8081. Min Act: -0.0000

Data Index: 1772196 (The Pile)

Max Activating Token Index: 673

Text #19

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.8310. Min Act: -0.0000

Data Index: 1269706 (The Pile)

Max Activating Token Index: 709