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

Dataset: The Pile

Neuron 1493 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: 1.2029. Min Range: -1.2029

Max Act: 1.2029. Min Act: -0.0000

Data Index: 126645 (The Pile)

Max Activating Token Index: 471

Text #1

Max Range: 1.2029. Min Range: -1.2029

Max Act: 1.0192. Min Act: -0.0000

Data Index: 70197 (The Pile)

Max Activating Token Index: 76

Text #2

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9773. Min Act: -0.0000

Data Index: 1412463 (The Pile)

Max Activating Token Index: 1005

Text #3

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9481. Min Act: -0.0000

Data Index: 1148570 (The Pile)

Max Activating Token Index: 417

Text #4

Max Range: 1.2029. Min Range: -1.2029

Max Act: 1.0061. Min Act: -0.0000

Data Index: 1335195 (The Pile)

Max Activating Token Index: 574

Text #5

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9349. Min Act: -0.0000

Data Index: 773297 (The Pile)

Max Activating Token Index: 602

Text #6

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8789. Min Act: -0.0000

Data Index: 491514 (The Pile)

Max Activating Token Index: 977

Text #7

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8923. Min Act: -0.0000

Data Index: 876139 (The Pile)

Max Activating Token Index: 620

Text #8

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9063. Min Act: -0.0000

Data Index: 1684259 (The Pile)

Max Activating Token Index: 943

Text #9

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8748. Min Act: -0.0000

Data Index: 1358481 (The Pile)

Max Activating Token Index: 158

Text #10

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8465. Min Act: -0.0000

Data Index: 1286777 (The Pile)

Max Activating Token Index: 284

Text #11

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8294. Min Act: -0.0000

Data Index: 1932309 (The Pile)

Max Activating Token Index: 606

Text #12

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.7834. Min Act: -0.0000

Data Index: 1772290 (The Pile)

Max Activating Token Index: 825

Text #13

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8479. Min Act: -0.0000

Data Index: 1495317 (The Pile)

Max Activating Token Index: 721

Text #14

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8809. Min Act: -0.0000

Data Index: 1472595 (The Pile)

Max Activating Token Index: 44

Text #15

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8444. Min Act: -0.0000

Data Index: 564962 (The Pile)

Max Activating Token Index: 573

Text #16

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8156. Min Act: -0.0000

Data Index: 1273291 (The Pile)

Max Activating Token Index: 755

Text #17

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8396. Min Act: -0.0000

Data Index: 1970375 (The Pile)

Max Activating Token Index: 384

Text #18

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8011. Min Act: -0.0000

Data Index: 1320605 (The Pile)

Max Activating Token Index: 888

Text #19

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9137. Min Act: -0.0000

Data Index: 47895 (The Pile)

Max Activating Token Index: 755