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

Dataset: The Pile

Neuron 3180 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: 1.8574. Min Range: -1.8574

Max Act: 1.8574. Min Act: -0.0000

Data Index: 27145 (The Pile)

Max Activating Token Index: 453

Text #1

Max Range: 1.8574. Min Range: -1.8574

Max Act: 1.7538. Min Act: -0.0000

Data Index: 953448 (The Pile)

Max Activating Token Index: 615

Text #2

Max Range: 1.8574. Min Range: -1.8574

Max Act: 1.8107. Min Act: -0.0000

Data Index: 1220135 (The Pile)

Max Activating Token Index: 736

Text #3

Max Range: 1.8574. Min Range: -1.8574

Max Act: 1.5642. Min Act: -0.0000

Data Index: 1391892 (The Pile)

Max Activating Token Index: 727

Text #4

Max Range: 1.8574. Min Range: -1.8574

Max Act: 1.6816. Min Act: -0.0000

Data Index: 892882 (The Pile)

Max Activating Token Index: 531

Text #5

Max Range: 1.8574. Min Range: -1.8574

Max Act: 1.5772. Min Act: -0.0000

Data Index: 266377 (The Pile)

Max Activating Token Index: 852

Text #6

Max Range: 1.8574. Min Range: -1.8574

Max Act: 1.4569. Min Act: -0.0000

Data Index: 498988 (The Pile)

Max Activating Token Index: 652

Text #7

Max Range: 1.8574. Min Range: -1.8574

Max Act: 1.3456. Min Act: -0.0000

Data Index: 253026 (The Pile)

Max Activating Token Index: 311

Text #8

Max Range: 1.8574. Min Range: -1.8574

Max Act: 1.4732. Min Act: -0.0000

Data Index: 221112 (The Pile)

Max Activating Token Index: 582

Text #9

Max Range: 1.8574. Min Range: -1.8574

Max Act: 1.5343. Min Act: -0.0000

Data Index: 486886 (The Pile)

Max Activating Token Index: 772

Text #10

Max Range: 1.8574. Min Range: -1.8574

Max Act: 1.4149. Min Act: -0.0000

Data Index: 1592425 (The Pile)

Max Activating Token Index: 412

Text #11

Max Range: 1.8574. Min Range: -1.8574

Max Act: 1.3365. Min Act: -0.0000

Data Index: 428552 (The Pile)

Max Activating Token Index: 506

Text #12

Max Range: 1.8574. Min Range: -1.8574

Max Act: 1.3387. Min Act: -0.0000

Data Index: 432254 (The Pile)

Max Activating Token Index: 560

Text #13

Max Range: 1.8574. Min Range: -1.8574

Max Act: 1.4725. Min Act: -0.0000

Data Index: 727815 (The Pile)

Max Activating Token Index: 467

Text #14

Max Range: 1.8574. Min Range: -1.8574

Max Act: 1.3325. Min Act: -0.0000

Data Index: 1914798 (The Pile)

Max Activating Token Index: 211

Text #15

Max Range: 1.8574. Min Range: -1.8574

Max Act: 1.2985. Min Act: -0.0000

Data Index: 1593606 (The Pile)

Max Activating Token Index: 283

Text #16

Max Range: 1.8574. Min Range: -1.8574

Max Act: 1.3795. Min Act: -0.0000

Data Index: 82709 (The Pile)

Max Activating Token Index: 546

Text #17

Max Range: 1.8574. Min Range: -1.8574

Max Act: 1.2867. Min Act: -0.0000

Data Index: 994384 (The Pile)

Max Activating Token Index: 524

Text #18

Max Range: 1.8574. Min Range: -1.8574

Max Act: 1.2732. Min Act: -0.0000

Data Index: 1653372 (The Pile)

Max Activating Token Index: 713

Text #19

Max Range: 1.8574. Min Range: -1.8574

Max Act: 1.2761. Min Act: -0.0000

Data Index: 1899939 (The Pile)

Max Activating Token Index: 560