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

Dataset: The Pile

Neuron 4745 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: 0.8445. Min Range: -0.8445

Max Act: 0.8445. Min Act: -0.0000

Data Index: 326282 (The Pile)

Max Activating Token Index: 502

Text #1

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7017. Min Act: -0.0000

Data Index: 964287 (The Pile)

Max Activating Token Index: 114

Text #2

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6949. Min Act: -0.0000

Data Index: 1463711 (The Pile)

Max Activating Token Index: 805

Text #3

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1475490 (The Pile)

Max Activating Token Index: 341

Text #4

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6657. Min Act: -0.0000

Data Index: 62114 (The Pile)

Max Activating Token Index: 398

Text #5

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6908. Min Act: -0.0000

Data Index: 453896 (The Pile)

Max Activating Token Index: 1020

Text #6

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6864. Min Act: -0.0000

Data Index: 713420 (The Pile)

Max Activating Token Index: 831

Text #7

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7027. Min Act: -0.0000

Data Index: 971521 (The Pile)

Max Activating Token Index: 1014

Text #8

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6530. Min Act: -0.0000

Data Index: 979144 (The Pile)

Max Activating Token Index: 75

Text #9

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6358. Min Act: -0.0000

Data Index: 299126 (The Pile)

Max Activating Token Index: 531

Text #10

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1934906 (The Pile)

Max Activating Token Index: 27

Text #11

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6567. Min Act: -0.0000

Data Index: 1345757 (The Pile)

Max Activating Token Index: 174

Text #12

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5681. Min Act: -0.0000

Data Index: 1250413 (The Pile)

Max Activating Token Index: 393

Text #13

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6232. Min Act: -0.0000

Data Index: 1211406 (The Pile)

Max Activating Token Index: 272

Text #14

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6167. Min Act: -0.0000

Data Index: 1069449 (The Pile)

Max Activating Token Index: 89

Text #15

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6583. Min Act: -0.0000

Data Index: 451399 (The Pile)

Max Activating Token Index: 797

Text #16

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6090. Min Act: -0.0000

Data Index: 1235843 (The Pile)

Max Activating Token Index: 565

Text #17

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6287. Min Act: -0.0000

Data Index: 1489253 (The Pile)

Max Activating Token Index: 281

Text #18

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6262. Min Act: -0.0000

Data Index: 1661101 (The Pile)

Max Activating Token Index: 226

Text #19

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6613. Min Act: -0.0000

Data Index: 125983 (The Pile)

Max Activating Token Index: 1016