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

Dataset: The Pile

Neuron 4093 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: 7.5113. Min Range: -7.5113

Max Act: 7.5113. Min Act: -0.0000

Data Index: 1228628 (The Pile)

Max Activating Token Index: 560

Text #1

Max Range: 7.5113. Min Range: -7.5113

Max Act: 7.2691. Min Act: -0.0000

Data Index: 1185561 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 7.5113. Min Range: -7.5113

Max Act: 7.3514. Min Act: -0.0000

Data Index: 1436978 (The Pile)

Max Activating Token Index: 806

Text #3

Max Range: 7.5113. Min Range: -7.5113

Max Act: 7.1610. Min Act: -0.0000

Data Index: 1198552 (The Pile)

Max Activating Token Index: 893

Text #4

Max Range: 7.5113. Min Range: -7.5113

Max Act: 6.7992. Min Act: -0.0000

Data Index: 468066 (The Pile)

Max Activating Token Index: 505

Text #5

Max Range: 7.5113. Min Range: -7.5113

Max Act: 6.7535. Min Act: -0.0000

Data Index: 1490227 (The Pile)

Max Activating Token Index: 379

Text #6

Max Range: 7.5113. Min Range: -7.5113

Max Act: 6.5564. Min Act: -0.0000

Data Index: 1980757 (The Pile)

Max Activating Token Index: 368

Text #7

Max Range: 7.5113. Min Range: -7.5113

Max Act: 6.7286. Min Act: -0.0000

Data Index: 942930 (The Pile)

Max Activating Token Index: 220

Text #8

Max Range: 7.5113. Min Range: -7.5113

Max Act: 6.4944. Min Act: -0.0000

Data Index: 1630631 (The Pile)

Max Activating Token Index: 81

Text #9

Max Range: 7.5113. Min Range: -7.5113

Max Act: 6.3209. Min Act: -0.0000

Data Index: 524303 (The Pile)

Max Activating Token Index: 105

Text #10

Max Range: 7.5113. Min Range: -7.5113

Max Act: 6.4848. Min Act: -0.0000

Data Index: 1961258 (The Pile)

Max Activating Token Index: 98

Text #11

Max Range: 7.5113. Min Range: -7.5113

Max Act: 6.5202. Min Act: -0.0000

Data Index: 49499 (The Pile)

Max Activating Token Index: 441

Text #12

Max Range: 7.5113. Min Range: -7.5113

Max Act: 6.3928. Min Act: -0.0000

Data Index: 1438231 (The Pile)

Max Activating Token Index: 59

Text #13

Max Range: 7.5113. Min Range: -7.5113

Max Act: 6.3924. Min Act: -0.0000

Data Index: 1228327 (The Pile)

Max Activating Token Index: 752

Text #14

Max Range: 7.5113. Min Range: -7.5113

Max Act: 6.1769. Min Act: -0.0000

Data Index: 189677 (The Pile)

Max Activating Token Index: 686

Text #15

Max Range: 7.5113. Min Range: -7.5113

Max Act: 6.5505. Min Act: -0.0000

Data Index: 104070 (The Pile)

Max Activating Token Index: 152

Text #16

Max Range: 7.5113. Min Range: -7.5113

Max Act: 6.4177. Min Act: -0.0000

Data Index: 1352688 (The Pile)

Max Activating Token Index: 458

Text #17

Max Range: 7.5113. Min Range: -7.5113

Max Act: 6.2087. Min Act: -0.0000

Data Index: 1758617 (The Pile)

Max Activating Token Index: 384

Text #18

Max Range: 7.5113. Min Range: -7.5113

Max Act: 5.8398. Min Act: -0.0000

Data Index: 427601 (The Pile)

Max Activating Token Index: 595

Text #19

Max Range: 7.5113. Min Range: -7.5113

Max Act: 6.2189. Min Act: -0.0000

Data Index: 296711 (The Pile)

Max Activating Token Index: 507