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

Dataset: The Pile

Neuron 3933 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1552624 (The Pile)

Max Activating Token Index: 319

Text #1

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3459. Min Act: -0.0000

Data Index: 1098716 (The Pile)

Max Activating Token Index: 605

Text #2

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3925. Min Act: -0.0000

Data Index: 619381 (The Pile)

Max Activating Token Index: 687

Text #3

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3506. Min Act: -0.0000

Data Index: 634097 (The Pile)

Max Activating Token Index: 432

Text #4

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3696. Min Act: -0.0000

Data Index: 267778 (The Pile)

Max Activating Token Index: 827

Text #5

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3336. Min Act: -0.0000

Data Index: 1527633 (The Pile)

Max Activating Token Index: 448

Text #6

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1929390 (The Pile)

Max Activating Token Index: 980

Text #7

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3215. Min Act: -0.0000

Data Index: 1698913 (The Pile)

Max Activating Token Index: 927

Text #8

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3071. Min Act: -0.0000

Data Index: 630091 (The Pile)

Max Activating Token Index: 416

Text #9

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2962. Min Act: -0.0000

Data Index: 936467 (The Pile)

Max Activating Token Index: 250

Text #10

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3264. Min Act: -0.0000

Data Index: 203946 (The Pile)

Max Activating Token Index: 647

Text #11

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3103. Min Act: -0.0000

Data Index: 1811455 (The Pile)

Max Activating Token Index: 712

Text #12

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3164. Min Act: -0.0000

Data Index: 1234331 (The Pile)

Max Activating Token Index: 712

Text #13

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3134. Min Act: -0.0000

Data Index: 232706 (The Pile)

Max Activating Token Index: 586

Text #14

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2926. Min Act: -0.0000

Data Index: 406000 (The Pile)

Max Activating Token Index: 715

Text #15

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3076. Min Act: -0.0000

Data Index: 1996858 (The Pile)

Max Activating Token Index: 589

Text #16

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2956. Min Act: -0.0000

Data Index: 1633850 (The Pile)

Max Activating Token Index: 30

Text #17

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3267. Min Act: -0.0000

Data Index: 1119977 (The Pile)

Max Activating Token Index: 572

Text #18

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3089. Min Act: -0.0000

Data Index: 78018 (The Pile)

Max Activating Token Index: 664

Text #19

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3128. Min Act: -0.0000

Data Index: 1423098 (The Pile)

Max Activating Token Index: 456