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

Dataset: The Pile

Neuron 4734 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3501. Min Range: -1.3501

Max Act: 1.3501. Min Act: -0.0000

Data Index: 1471709 (The Pile)

Max Activating Token Index: 579

Text #1

Max Range: 1.3501. Min Range: -1.3501

Max Act: 1.0548. Min Act: -0.0000

Data Index: 1762851 (The Pile)

Max Activating Token Index: 909

Text #2

Max Range: 1.3501. Min Range: -1.3501

Max Act: 0.9527. Min Act: -0.0000

Data Index: 1648233 (The Pile)

Max Activating Token Index: 557

Text #3

Max Range: 1.3501. Min Range: -1.3501

Max Act: 0.9442. Min Act: -0.0000

Data Index: 147467 (The Pile)

Max Activating Token Index: 364

Text #4

Max Range: 1.3501. Min Range: -1.3501

Max Act: 0.9554. Min Act: -0.0000

Data Index: 708022 (The Pile)

Max Activating Token Index: 133

Text #5

Max Range: 1.3501. Min Range: -1.3501

Max Act: 0.8820. Min Act: -0.0000

Data Index: 856144 (The Pile)

Max Activating Token Index: 328

Text #6

Max Range: 1.3501. Min Range: -1.3501

Max Act: 0.8793. Min Act: -0.0000

Data Index: 1332961 (The Pile)

Max Activating Token Index: 1010

Text #7

Max Range: 1.3501. Min Range: -1.3501

Max Act: 0.8372. Min Act: -0.0000

Data Index: 1672695 (The Pile)

Max Activating Token Index: 351

Text #8

Max Range: 1.3501. Min Range: -1.3501

Max Act: 0.7632. Min Act: -0.0000

Data Index: 1399958 (The Pile)

Max Activating Token Index: 50

Text #9

Max Range: 1.3501. Min Range: -1.3501

Max Act: 0.8107. Min Act: -0.0000

Data Index: 753616 (The Pile)

Max Activating Token Index: 411

Text #10

Max Range: 1.3501. Min Range: -1.3501

Max Act: 0.7824. Min Act: -0.0000

Data Index: 1038360 (The Pile)

Max Activating Token Index: 554

Text #11

Max Range: 1.3501. Min Range: -1.3501

Max Act: 0.7974. Min Act: -0.0000

Data Index: 854747 (The Pile)

Max Activating Token Index: 480

Text #12

Max Range: 1.3501. Min Range: -1.3501

Max Act: 0.7724. Min Act: -0.0000

Data Index: 61291 (The Pile)

Max Activating Token Index: 45

Text #13

Max Range: 1.3501. Min Range: -1.3501

Max Act: 0.7852. Min Act: -0.0000

Data Index: 273168 (The Pile)

Max Activating Token Index: 669

Text #14

Max Range: 1.3501. Min Range: -1.3501

Max Act: 0.7356. Min Act: -0.0000

Data Index: 764659 (The Pile)

Max Activating Token Index: 338

Text #15

Max Range: 1.3501. Min Range: -1.3501

Max Act: 0.6812. Min Act: -0.0000

Data Index: 1767923 (The Pile)

Max Activating Token Index: 150

Text #16

Max Range: 1.3501. Min Range: -1.3501

Max Act: 0.8324. Min Act: -0.0000

Data Index: 1079938 (The Pile)

Max Activating Token Index: 903

Text #17

Max Range: 1.3501. Min Range: -1.3501

Max Act: 0.7077. Min Act: -0.0000

Data Index: 1415037 (The Pile)

Max Activating Token Index: 597

Text #18

Max Range: 1.3501. Min Range: -1.3501

Max Act: 0.7175. Min Act: -0.0000

Data Index: 839693 (The Pile)

Max Activating Token Index: 668

Text #19

Max Range: 1.3501. Min Range: -1.3501

Max Act: 0.7359. Min Act: -0.0000

Data Index: 601370 (The Pile)

Max Activating Token Index: 335