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

Dataset: The Pile

Neuron 3103 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: 1.2029. Min Range: -1.2029

Max Act: 1.2029. Min Act: -0.0000

Data Index: 1395897 (The Pile)

Max Activating Token Index: 29

Text #1

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8983. Min Act: -0.0000

Data Index: 1866483 (The Pile)

Max Activating Token Index: 977

Text #2

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9368. Min Act: -0.0000

Data Index: 1712769 (The Pile)

Max Activating Token Index: 21

Text #3

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8779. Min Act: -0.0000

Data Index: 481605 (The Pile)

Max Activating Token Index: 355

Text #4

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9215. Min Act: -0.0000

Data Index: 1154469 (The Pile)

Max Activating Token Index: 97

Text #5

Max Range: 1.2029. Min Range: -1.2029

Max Act: 1.0327. Min Act: -0.0000

Data Index: 1383285 (The Pile)

Max Activating Token Index: 147

Text #6

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8561. Min Act: -0.0000

Data Index: 1355435 (The Pile)

Max Activating Token Index: 807

Text #7

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9005. Min Act: -0.0000

Data Index: 186080 (The Pile)

Max Activating Token Index: 393

Text #8

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8481. Min Act: -0.0000

Data Index: 45907 (The Pile)

Max Activating Token Index: 366

Text #9

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9042. Min Act: -0.0000

Data Index: 60383 (The Pile)

Max Activating Token Index: 901

Text #10

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8435. Min Act: -0.0000

Data Index: 1398534 (The Pile)

Max Activating Token Index: 465

Text #11

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8010. Min Act: -0.0000

Data Index: 818548 (The Pile)

Max Activating Token Index: 156

Text #12

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8048. Min Act: -0.0000

Data Index: 321950 (The Pile)

Max Activating Token Index: 84

Text #13

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.7970. Min Act: -0.0000

Data Index: 1158009 (The Pile)

Max Activating Token Index: 685

Text #14

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8430. Min Act: -0.0000

Data Index: 1995136 (The Pile)

Max Activating Token Index: 826

Text #15

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.7921. Min Act: -0.0000

Data Index: 801181 (The Pile)

Max Activating Token Index: 316

Text #16

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.7483. Min Act: -0.0000

Data Index: 507733 (The Pile)

Max Activating Token Index: 908

Text #17

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1970343 (The Pile)

Max Activating Token Index: 80

Text #18

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.7724. Min Act: -0.0000

Data Index: 649683 (The Pile)

Max Activating Token Index: 250

Text #19

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.7625. Min Act: -0.0000

Data Index: 1422268 (The Pile)

Max Activating Token Index: 141