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

Dataset: The Pile

Neuron 2548 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.5215. Min Act: -0.0000

Data Index: 1095574 (The Pile)

Max Activating Token Index: 656

Text #1

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.2752. Min Act: -0.0000

Data Index: 687080 (The Pile)

Max Activating Token Index: 667

Text #2

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.2357. Min Act: -0.0000

Data Index: 1465797 (The Pile)

Max Activating Token Index: 297

Text #3

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.3471. Min Act: -0.0000

Data Index: 137841 (The Pile)

Max Activating Token Index: 622

Text #4

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.2397. Min Act: -0.0000

Data Index: 676887 (The Pile)

Max Activating Token Index: 146

Text #5

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.1792. Min Act: -0.0000

Data Index: 948249 (The Pile)

Max Activating Token Index: 359

Text #6

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.1597. Min Act: -0.0000

Data Index: 1995531 (The Pile)

Max Activating Token Index: 12

Text #7

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.3514. Min Act: -0.0000

Data Index: 1538722 (The Pile)

Max Activating Token Index: 569

Text #8

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.2206. Min Act: -0.0000

Data Index: 1463271 (The Pile)

Max Activating Token Index: 436

Text #9

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.1264. Min Act: -0.0000

Data Index: 1550395 (The Pile)

Max Activating Token Index: 819

Text #10

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.0448. Min Act: -0.0000

Data Index: 81242 (The Pile)

Max Activating Token Index: 734

Text #11

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.1886. Min Act: 0.0000

Data Index: 1144753 (The Pile)

Max Activating Token Index: 44

Text #12

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.1748. Min Act: -0.0000

Data Index: 314643 (The Pile)

Max Activating Token Index: 437

Text #13

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.1201. Min Act: -0.0000

Data Index: 738857 (The Pile)

Max Activating Token Index: 803

Text #14

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.0212. Min Act: -0.0000

Data Index: 167870 (The Pile)

Max Activating Token Index: 927

Text #15

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.1316. Min Act: -0.0000

Data Index: 550702 (The Pile)

Max Activating Token Index: 47

Text #16

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.1117. Min Act: -0.0000

Data Index: 137454 (The Pile)

Max Activating Token Index: 344

Text #17

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.1165. Min Act: -0.0000

Data Index: 370998 (The Pile)

Max Activating Token Index: 798

Text #18

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.1203. Min Act: -0.0000

Data Index: 374638 (The Pile)

Max Activating Token Index: 803

Text #19

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.1255. Min Act: -0.0000

Data Index: 1791134 (The Pile)

Max Activating Token Index: 444