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

Dataset: The Pile

Neuron 243 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: 1.1471. Min Range: -1.1471

Max Act: 1.1471. Min Act: -0.0000

Data Index: 1689924 (The Pile)

Max Activating Token Index: 232

Text #1

Max Range: 1.1471. Min Range: -1.1471

Max Act: 1.1085. Min Act: -0.0000

Data Index: 777446 (The Pile)

Max Activating Token Index: 486

Text #2

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9899. Min Act: -0.0000

Data Index: 1896830 (The Pile)

Max Activating Token Index: 332

Text #3

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9992. Min Act: -0.0000

Data Index: 170001 (The Pile)

Max Activating Token Index: 369

Text #4

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9034. Min Act: -0.0000

Data Index: 1023214 (The Pile)

Max Activating Token Index: 220

Text #5

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9477. Min Act: -0.0000

Data Index: 614985 (The Pile)

Max Activating Token Index: 434

Text #6

Max Range: 1.1471. Min Range: -1.1471

Max Act: 1.0167. Min Act: -0.0000

Data Index: 287097 (The Pile)

Max Activating Token Index: 761

Text #7

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.8188. Min Act: -0.0000

Data Index: 1819454 (The Pile)

Max Activating Token Index: 179

Text #8

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.8512. Min Act: -0.0000

Data Index: 751479 (The Pile)

Max Activating Token Index: 112

Text #9

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9115. Min Act: -0.0000

Data Index: 1635466 (The Pile)

Max Activating Token Index: 137

Text #10

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.7848. Min Act: -0.0000

Data Index: 221506 (The Pile)

Max Activating Token Index: 506

Text #11

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.8397. Min Act: -0.0000

Data Index: 1958029 (The Pile)

Max Activating Token Index: 217

Text #12

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.7252. Min Act: -0.0000

Data Index: 490669 (The Pile)

Max Activating Token Index: 463

Text #13

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.7218. Min Act: -0.0000

Data Index: 403298 (The Pile)

Max Activating Token Index: 524

Text #14

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.8442. Min Act: -0.0000

Data Index: 1202619 (The Pile)

Max Activating Token Index: 89

Text #15

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.7819. Min Act: -0.0000

Data Index: 286910 (The Pile)

Max Activating Token Index: 442

Text #16

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.7738. Min Act: -0.0000

Data Index: 1662912 (The Pile)

Max Activating Token Index: 204

Text #17

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.8093. Min Act: -0.0000

Data Index: 685414 (The Pile)

Max Activating Token Index: 167

Text #18

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.7701. Min Act: -0.0000

Data Index: 604556 (The Pile)

Max Activating Token Index: 257

Text #19

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.7220. Min Act: -0.0000

Data Index: 1945059 (The Pile)

Max Activating Token Index: 168