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

Dataset: The Pile

Neuron 739 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: 1.5609. Min Range: -1.5609

Max Act: 1.5609. Min Act: -0.0000

Data Index: 260260 (The Pile)

Max Activating Token Index: 529

Text #1

Max Range: 1.5609. Min Range: -1.5609

Max Act: 1.5495. Min Act: -0.0000

Data Index: 417630 (The Pile)

Max Activating Token Index: 869

Text #2

Max Range: 1.5609. Min Range: -1.5609

Max Act: 1.5299. Min Act: -0.0000

Data Index: 938319 (The Pile)

Max Activating Token Index: 483

Text #3

Max Range: 1.5609. Min Range: -1.5609

Max Act: 1.1927. Min Act: -0.0000

Data Index: 321680 (The Pile)

Max Activating Token Index: 357

Text #4

Max Range: 1.5609. Min Range: -1.5609

Max Act: 1.3330. Min Act: -0.0000

Data Index: 528329 (The Pile)

Max Activating Token Index: 595

Text #5

Max Range: 1.5609. Min Range: -1.5609

Max Act: 1.2460. Min Act: -0.0000

Data Index: 1052787 (The Pile)

Max Activating Token Index: 352

Text #6

Max Range: 1.5609. Min Range: -1.5609

Max Act: 1.2321. Min Act: -0.0000

Data Index: 1258803 (The Pile)

Max Activating Token Index: 427

Text #7

Max Range: 1.5609. Min Range: -1.5609

Max Act: 1.2973. Min Act: -0.0000

Data Index: 963605 (The Pile)

Max Activating Token Index: 927

Text #8

Max Range: 1.5609. Min Range: -1.5609

Max Act: 1.2747. Min Act: -0.0000

Data Index: 386247 (The Pile)

Max Activating Token Index: 112

Text #9

Max Range: 1.5609. Min Range: -1.5609

Max Act: 1.1989. Min Act: -0.0000

Data Index: 339227 (The Pile)

Max Activating Token Index: 215

Text #10

Max Range: 1.5609. Min Range: -1.5609

Max Act: 1.2033. Min Act: -0.0000

Data Index: 117390 (The Pile)

Max Activating Token Index: 971

Text #11

Max Range: 1.5609. Min Range: -1.5609

Max Act: 1.1140. Min Act: -0.0000

Data Index: 997490 (The Pile)

Max Activating Token Index: 423

Text #12

Max Range: 1.5609. Min Range: -1.5609

Max Act: 1.1719. Min Act: -0.0000

Data Index: 1660857 (The Pile)

Max Activating Token Index: 222

Text #13

Max Range: 1.5609. Min Range: -1.5609

Max Act: 1.1561. Min Act: -0.0000

Data Index: 1478587 (The Pile)

Max Activating Token Index: 216

Text #14

Max Range: 1.5609. Min Range: -1.5609

Max Act: 1.1346. Min Act: -0.0000

Data Index: 1840744 (The Pile)

Max Activating Token Index: 123

Text #15

Max Range: 1.5609. Min Range: -1.5609

Max Act: 1.1150. Min Act: -0.0000

Data Index: 406523 (The Pile)

Max Activating Token Index: 297

Text #16

Max Range: 1.5609. Min Range: -1.5609

Max Act: 1.0455. Min Act: -0.0000

Data Index: 1940858 (The Pile)

Max Activating Token Index: 307

Text #17

Max Range: 1.5609. Min Range: -1.5609

Max Act: 1.1049. Min Act: -0.0000

Data Index: 330285 (The Pile)

Max Activating Token Index: 97

Text #18

Max Range: 1.5609. Min Range: -1.5609

Max Act: 1.0936. Min Act: -0.0000

Data Index: 306040 (The Pile)

Max Activating Token Index: 606

Text #19

Max Range: 1.5609. Min Range: -1.5609

Max Act: 1.0973. Min Act: -0.0000

Data Index: 220575 (The Pile)

Max Activating Token Index: 945