Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 952 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.7493. Min Act: -0.0000

Data Index: 1125743 (The Pile)

Max Activating Token Index: 77

Text #1

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.7975. Min Act: -0.0000

Data Index: 1494103 (The Pile)

Max Activating Token Index: 407

Text #2

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.7017. Min Act: -0.0000

Data Index: 1059569 (The Pile)

Max Activating Token Index: 1021

Text #3

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.6882. Min Act: -0.0000

Data Index: 792666 (The Pile)

Max Activating Token Index: 492

Text #4

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.7002. Min Act: -0.0000

Data Index: 1208499 (The Pile)

Max Activating Token Index: 317

Text #5

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1739067 (The Pile)

Max Activating Token Index: 480

Text #6

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.6558. Min Act: -0.0000

Data Index: 755932 (The Pile)

Max Activating Token Index: 330

Text #7

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.6078. Min Act: -0.0000

Data Index: 1169886 (The Pile)

Max Activating Token Index: 61

Text #8

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.6264. Min Act: -0.0000

Data Index: 320472 (The Pile)

Max Activating Token Index: 339

Text #9

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1234315 (The Pile)

Max Activating Token Index: 150

Text #10

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.5668. Min Act: -0.0000

Data Index: 1499273 (The Pile)

Max Activating Token Index: 106

Text #11

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1595992 (The Pile)

Max Activating Token Index: 215

Text #12

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1839478 (The Pile)

Max Activating Token Index: 512

Text #13

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.6084. Min Act: -0.0000

Data Index: 467022 (The Pile)

Max Activating Token Index: 686

Text #14

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.5835. Min Act: -0.0000

Data Index: 1975491 (The Pile)

Max Activating Token Index: 882

Text #15

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.5755. Min Act: -0.0000

Data Index: 430031 (The Pile)

Max Activating Token Index: 96

Text #16

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.5204. Min Act: -0.0000

Data Index: 1781878 (The Pile)

Max Activating Token Index: 878

Text #17

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.6282. Min Act: -0.0000

Data Index: 1588914 (The Pile)

Max Activating Token Index: 408

Text #18

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1878140 (The Pile)

Max Activating Token Index: 423

Text #19

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.5632. Min Act: -0.0000

Data Index: 1124575 (The Pile)

Max Activating Token Index: 545