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

Dataset: The Pile

Neuron 1233 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: 3.1631. Min Range: -3.1631

Max Act: 3.0764. Min Act: -0.0000

Data Index: 1366957 (The Pile)

Max Activating Token Index: 1012

Text #1

Max Range: 3.1631. Min Range: -3.1631

Max Act: 3.1631. Min Act: -0.0000

Data Index: 291501 (The Pile)

Max Activating Token Index: 768

Text #2

Max Range: 3.1631. Min Range: -3.1631

Max Act: 2.7134. Min Act: -0.0000

Data Index: 1534450 (The Pile)

Max Activating Token Index: 841

Text #3

Max Range: 3.1631. Min Range: -3.1631

Max Act: 2.4036. Min Act: -0.0000

Data Index: 1938139 (The Pile)

Max Activating Token Index: 103

Text #4

Max Range: 3.1631. Min Range: -3.1631

Max Act: 2.3721. Min Act: -0.0000

Data Index: 649571 (The Pile)

Max Activating Token Index: 495

Text #5

Max Range: 3.1631. Min Range: -3.1631

Max Act: 2.2911. Min Act: -0.0000

Data Index: 1332048 (The Pile)

Max Activating Token Index: 836

Text #6

Max Range: 3.1631. Min Range: -3.1631

Max Act: 2.3717. Min Act: -0.0000

Data Index: 1730755 (The Pile)

Max Activating Token Index: 312

Text #7

Max Range: 3.1631. Min Range: -3.1631

Max Act: 2.3529. Min Act: -0.0000

Data Index: 869605 (The Pile)

Max Activating Token Index: 985

Text #8

Max Range: 3.1631. Min Range: -3.1631

Max Act: 2.2896. Min Act: -0.0000

Data Index: 1351113 (The Pile)

Max Activating Token Index: 336

Text #9

Max Range: 3.1631. Min Range: -3.1631

Max Act: 2.4062. Min Act: -0.0000

Data Index: 1383710 (The Pile)

Max Activating Token Index: 734

Text #10

Max Range: 3.1631. Min Range: -3.1631

Max Act: 2.6707. Min Act: -0.0000

Data Index: 1819371 (The Pile)

Max Activating Token Index: 873

Text #11

Max Range: 3.1631. Min Range: -3.1631

Max Act: 2.0703. Min Act: -0.0000

Data Index: 1953095 (The Pile)

Max Activating Token Index: 959

Text #12

Max Range: 3.1631. Min Range: -3.1631

Max Act: 2.2628. Min Act: -0.0000

Data Index: 1103211 (The Pile)

Max Activating Token Index: 738

Text #13

Max Range: 3.1631. Min Range: -3.1631

Max Act: 2.1574. Min Act: -0.0000

Data Index: 864139 (The Pile)

Max Activating Token Index: 457

Text #14

Max Range: 3.1631. Min Range: -3.1631

Max Act: 2.3831. Min Act: -0.0000

Data Index: 891777 (The Pile)

Max Activating Token Index: 182

Text #15

Max Range: 3.1631. Min Range: -3.1631

Max Act: 2.2725. Min Act: -0.0000

Data Index: 222555 (The Pile)

Max Activating Token Index: 84

Text #16

Max Range: 3.1631. Min Range: -3.1631

Max Act: 2.2601. Min Act: -0.0000

Data Index: 15509 (The Pile)

Max Activating Token Index: 85

Text #17

Max Range: 3.1631. Min Range: -3.1631

Max Act: 2.2387. Min Act: -0.0000

Data Index: 1803799 (The Pile)

Max Activating Token Index: 192

Text #18

Max Range: 3.1631. Min Range: -3.1631

Max Act: 2.3162. Min Act: -0.0000

Data Index: 1530361 (The Pile)

Max Activating Token Index: 622

Text #19

Max Range: 3.1631. Min Range: -3.1631

Max Act: 2.3032. Min Act: -0.0000

Data Index: 1519347 (The Pile)

Max Activating Token Index: 1019