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

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

Neuron 3882 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5414. Min Range: -1.5414

Max Act: 1.5414. Min Act: -0.0001

Data Index: 162130 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 1.5414. Min Range: -1.5414

Max Act: 1.3754. Min Act: -0.0001

Data Index: 307440 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 1.5414. Min Range: -1.5414

Max Act: 1.3104. Min Act: -0.0001

Data Index: 461399 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 1.5414. Min Range: -1.5414

Max Act: 1.3415. Min Act: -0.0001

Data Index: 1253619 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 1.5414. Min Range: -1.5414

Max Act: 1.1687. Min Act: -0.0001

Data Index: 1119408 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 1.5414. Min Range: -1.5414

Max Act: 1.2366. Min Act: -0.0001

Data Index: 545908 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 1.5414. Min Range: -1.5414

Max Act: 1.1873. Min Act: -0.0001

Data Index: 947638 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 1.5414. Min Range: -1.5414

Max Act: 1.1899. Min Act: -0.0001

Data Index: 946368 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 1.5414. Min Range: -1.5414

Max Act: 1.0137. Min Act: -0.0001

Data Index: 19959 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 1.5414. Min Range: -1.5414

Max Act: 1.1143. Min Act: -0.0001

Data Index: 1116189 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 1.5414. Min Range: -1.5414

Max Act: 1.0999. Min Act: -0.0001

Data Index: 235741 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 1.5414. Min Range: -1.5414

Max Act: 1.0457. Min Act: -0.0001

Data Index: 578452 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 1.5414. Min Range: -1.5414

Max Act: 1.1663. Min Act: -0.0001

Data Index: 559984 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 1.5414. Min Range: -1.5414

Max Act: 1.1721. Min Act: -0.0001

Data Index: 217364 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 1.5414. Min Range: -1.5414

Max Act: 1.0013. Min Act: -0.0001

Data Index: 1244088 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 1.5414. Min Range: -1.5414

Max Act: 1.0878. Min Act: -0.0001

Data Index: 1002756 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 1.5414. Min Range: -1.5414

Max Act: 1.0921. Min Act: -0.0001

Data Index: 369956 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 1.5414. Min Range: -1.5414

Max Act: 1.1109. Min Act: -0.0001

Data Index: 218705 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 1.5414. Min Range: -1.5414

Max Act: 1.0149. Min Act: -0.0001

Data Index: 941438 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 1.5414. Min Range: -1.5414

Max Act: 1.0699. Min Act: -0.0001

Data Index: 861800 (C4 (Web Text))

Max Activating Token Index: 107