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

Dataset: The Pile

Neuron 4061 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.7117. Min Act: -0.0000

Data Index: 531972 (The Pile)

Max Activating Token Index: 966

Text #1

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.6657. Min Act: -0.0000

Data Index: 820997 (The Pile)

Max Activating Token Index: 289

Text #2

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.6239. Min Act: -0.0000

Data Index: 581001 (The Pile)

Max Activating Token Index: 937

Text #3

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.5322. Min Act: -0.0000

Data Index: 1474956 (The Pile)

Max Activating Token Index: 658

Text #4

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.5758. Min Act: -0.0000

Data Index: 1189107 (The Pile)

Max Activating Token Index: 286

Text #5

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.5188. Min Act: -0.0000

Data Index: 53598 (The Pile)

Max Activating Token Index: 623

Text #6

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.5745. Min Act: -0.0000

Data Index: 1613015 (The Pile)

Max Activating Token Index: 860

Text #7

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.4891. Min Act: -0.0000

Data Index: 1722456 (The Pile)

Max Activating Token Index: 832

Text #8

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1995324 (The Pile)

Max Activating Token Index: 476

Text #9

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.5333. Min Act: -0.0000

Data Index: 119589 (The Pile)

Max Activating Token Index: 156

Text #10

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.3885. Min Act: -0.0000

Data Index: 1831435 (The Pile)

Max Activating Token Index: 978

Text #11

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.4476. Min Act: -0.0000

Data Index: 901958 (The Pile)

Max Activating Token Index: 958

Text #12

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.4882. Min Act: -0.0000

Data Index: 938722 (The Pile)

Max Activating Token Index: 155

Text #13

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.4192. Min Act: -0.0000

Data Index: 1745952 (The Pile)

Max Activating Token Index: 772

Text #14

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.4584. Min Act: -0.0000

Data Index: 767534 (The Pile)

Max Activating Token Index: 411

Text #15

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.4332. Min Act: -0.0000

Data Index: 778682 (The Pile)

Max Activating Token Index: 1004

Text #16

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1676107 (The Pile)

Max Activating Token Index: 125

Text #17

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.4573. Min Act: -0.0000

Data Index: 1390139 (The Pile)

Max Activating Token Index: 121

Text #18

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1761583 (The Pile)

Max Activating Token Index: 418

Text #19

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.4541. Min Act: -0.0000

Data Index: 1668883 (The Pile)

Max Activating Token Index: 314