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

Dataset: The Pile

Neuron 3051 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.8080. Min Act: -0.0001

Data Index: 1666907 (The Pile)

Max Activating Token Index: 191

Text #1

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7555. Min Act: -0.0001

Data Index: 125613 (The Pile)

Max Activating Token Index: 554

Text #2

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6959. Min Act: -0.0001

Data Index: 636617 (The Pile)

Max Activating Token Index: 609

Text #3

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7515. Min Act: -0.0001

Data Index: 787592 (The Pile)

Max Activating Token Index: 569

Text #4

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7616. Min Act: -0.0001

Data Index: 954771 (The Pile)

Max Activating Token Index: 139

Text #5

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6855. Min Act: -0.0001

Data Index: 686903 (The Pile)

Max Activating Token Index: 628

Text #6

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6992. Min Act: -0.0001

Data Index: 1127588 (The Pile)

Max Activating Token Index: 890

Text #7

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7450. Min Act: -0.0001

Data Index: 176991 (The Pile)

Max Activating Token Index: 251

Text #8

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7498. Min Act: -0.0001

Data Index: 1317265 (The Pile)

Max Activating Token Index: 330

Text #9

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7405. Min Act: -0.0001

Data Index: 132171 (The Pile)

Max Activating Token Index: 11

Text #10

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6055. Min Act: -0.0001

Data Index: 646895 (The Pile)

Max Activating Token Index: 691

Text #11

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6566. Min Act: -0.0001

Data Index: 1583843 (The Pile)

Max Activating Token Index: 180

Text #12

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6598. Min Act: -0.0001

Data Index: 783782 (The Pile)

Max Activating Token Index: 478

Text #13

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6864. Min Act: -0.0001

Data Index: 1759875 (The Pile)

Max Activating Token Index: 130

Text #14

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6987. Min Act: -0.0001

Data Index: 1890198 (The Pile)

Max Activating Token Index: 50

Text #15

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6488. Min Act: -0.0001

Data Index: 76650 (The Pile)

Max Activating Token Index: 617

Text #16

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7148. Min Act: -0.0001

Data Index: 90569 (The Pile)

Max Activating Token Index: 1006

Text #17

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6611. Min Act: -0.0001

Data Index: 1936126 (The Pile)

Max Activating Token Index: 146

Text #18

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7014. Min Act: -0.0001

Data Index: 1097313 (The Pile)

Max Activating Token Index: 248

Text #19

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6542. Min Act: -0.0001

Data Index: 1136697 (The Pile)

Max Activating Token Index: 401