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

Dataset: The Pile

Neuron 2219 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: 1.1102. Min Range: -1.1102

Max Act: 1.1102. Min Act: -0.0000

Data Index: 304737 (The Pile)

Max Activating Token Index: 319

Text #1

Max Range: 1.1102. Min Range: -1.1102

Max Act: 1.0163. Min Act: -0.0000

Data Index: 1670863 (The Pile)

Max Activating Token Index: 609

Text #2

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.9891. Min Act: -0.0000

Data Index: 1863298 (The Pile)

Max Activating Token Index: 821

Text #3

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.9599. Min Act: -0.0000

Data Index: 1151255 (The Pile)

Max Activating Token Index: 72

Text #4

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.9158. Min Act: -0.0000

Data Index: 154727 (The Pile)

Max Activating Token Index: 371

Text #5

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.8397. Min Act: -0.0000

Data Index: 1736741 (The Pile)

Max Activating Token Index: 686

Text #6

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.8887. Min Act: -0.0000

Data Index: 203869 (The Pile)

Max Activating Token Index: 696

Text #7

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.8040. Min Act: -0.0000

Data Index: 1417716 (The Pile)

Max Activating Token Index: 375

Text #8

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.8267. Min Act: -0.0000

Data Index: 403664 (The Pile)

Max Activating Token Index: 228

Text #9

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.7962. Min Act: -0.0000

Data Index: 1546689 (The Pile)

Max Activating Token Index: 312

Text #10

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.8187. Min Act: -0.0000

Data Index: 289624 (The Pile)

Max Activating Token Index: 115

Text #11

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1867910 (The Pile)

Max Activating Token Index: 483

Text #12

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.7340. Min Act: -0.0000

Data Index: 520744 (The Pile)

Max Activating Token Index: 176

Text #13

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.7460. Min Act: -0.0000

Data Index: 1190983 (The Pile)

Max Activating Token Index: 157

Text #14

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.7606. Min Act: -0.0000

Data Index: 67457 (The Pile)

Max Activating Token Index: 439

Text #15

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.7555. Min Act: -0.0000

Data Index: 1794470 (The Pile)

Max Activating Token Index: 323

Text #16

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.7484. Min Act: -0.0000

Data Index: 1023442 (The Pile)

Max Activating Token Index: 8

Text #17

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.6945. Min Act: -0.0000

Data Index: 266114 (The Pile)

Max Activating Token Index: 275

Text #18

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.7130. Min Act: -0.0000

Data Index: 382966 (The Pile)

Max Activating Token Index: 816

Text #19

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.7548. Min Act: -0.0000

Data Index: 974442 (The Pile)

Max Activating Token Index: 203