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

Dataset: The Pile

Neuron 1625 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.9952. Min Act: -0.0000

Data Index: 967922 (The Pile)

Max Activating Token Index: 233

Text #1

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.9566. Min Act: -0.0000

Data Index: 1469513 (The Pile)

Max Activating Token Index: 239

Text #2

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.8724. Min Act: -0.0001

Data Index: 648342 (The Pile)

Max Activating Token Index: 85

Text #3

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.8708. Min Act: -0.0000

Data Index: 1162291 (The Pile)

Max Activating Token Index: 19

Text #4

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.8364. Min Act: -0.0000

Data Index: 1341760 (The Pile)

Max Activating Token Index: 1006

Text #5

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.8755. Min Act: -0.0000

Data Index: 1592060 (The Pile)

Max Activating Token Index: 1014

Text #6

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.8082. Min Act: -0.0001

Data Index: 1991953 (The Pile)

Max Activating Token Index: 175

Text #7

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.8061. Min Act: -0.0000

Data Index: 783544 (The Pile)

Max Activating Token Index: 862

Text #8

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.7620. Min Act: -0.0000

Data Index: 4216 (The Pile)

Max Activating Token Index: 199

Text #9

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.7965. Min Act: -0.0000

Data Index: 304172 (The Pile)

Max Activating Token Index: 826

Text #10

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.7650. Min Act: -0.0000

Data Index: 1593650 (The Pile)

Max Activating Token Index: 427

Text #11

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.7621. Min Act: -0.0000

Data Index: 1381170 (The Pile)

Max Activating Token Index: 888

Text #12

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.7770. Min Act: -0.0000

Data Index: 184907 (The Pile)

Max Activating Token Index: 218

Text #13

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.8080. Min Act: -0.0000

Data Index: 472324 (The Pile)

Max Activating Token Index: 1012

Text #14

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.7704. Min Act: -0.0001

Data Index: 964913 (The Pile)

Max Activating Token Index: 482

Text #15

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.7807. Min Act: -0.0001

Data Index: 969437 (The Pile)

Max Activating Token Index: 956

Text #16

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.7112. Min Act: -0.0000

Data Index: 940068 (The Pile)

Max Activating Token Index: 233

Text #17

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.7960. Min Act: -0.0000

Data Index: 1699537 (The Pile)

Max Activating Token Index: 616

Text #18

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.8009. Min Act: -0.0000

Data Index: 1300870 (The Pile)

Max Activating Token Index: 365

Text #19

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.7929. Min Act: -0.0001

Data Index: 194407 (The Pile)

Max Activating Token Index: 883