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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3013 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.8876. Min Act: -0.0001

Data Index: 1127566 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.5903. Min Act: -0.0001

Data Index: 834660 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.5667. Min Act: -0.0000

Data Index: 1325272 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.5084. Min Act: -0.0001

Data Index: 132605 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.8332. Min Act: -0.0000

Data Index: 849095 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.6059. Min Act: -0.0000

Data Index: 825856 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.5717. Min Act: -0.0001

Data Index: 886247 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.5501. Min Act: -0.0001

Data Index: 535979 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.3726. Min Act: -0.0000

Data Index: 569299 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.3754. Min Act: -0.0001

Data Index: 756536 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.4119. Min Act: -0.0000

Data Index: 656236 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.1868. Min Act: -0.0001

Data Index: 1043500 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.3768. Min Act: -0.0000

Data Index: 800564 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.5424. Min Act: -0.0000

Data Index: 1185572 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.3558. Min Act: -0.0001

Data Index: 260757 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.5039. Min Act: -0.0001

Data Index: 279987 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.4538. Min Act: -0.0001

Data Index: 669306 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.2198. Min Act: -0.0000

Data Index: 1253043 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.2806. Min Act: -0.0001

Data Index: 1269936 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.2266. Min Act: -0.0001

Data Index: 958938 (C4 (Web Text))

Max Activating Token Index: 806