Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1138 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1351. Min Range: -1.1351

Max Act: 1.0988. Min Act: -0.0000

Data Index: 491781 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 1.1351. Min Range: -1.1351

Max Act: 1.0526. Min Act: -0.0001

Data Index: 235495 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 1.1351. Min Range: -1.1351

Max Act: 1.1351. Min Act: -0.0000

Data Index: 693186 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 1.1351. Min Range: -1.1351

Max Act: 1.0476. Min Act: -0.0000

Data Index: 398190 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.9804. Min Act: -0.0000

Data Index: 987701 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 1.1351. Min Range: -1.1351

Max Act: 1.0027. Min Act: -0.0000

Data Index: 1050514 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 1.1351. Min Range: -1.1351

Max Act: 1.0207. Min Act: -0.0000

Data Index: 1150334 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 1.1351. Min Range: -1.1351

Max Act: 1.0117. Min Act: -0.0000

Data Index: 716195 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.9885. Min Act: -0.0000

Data Index: 123287 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.9487. Min Act: -0.0000

Data Index: 702436 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 1.1351. Min Range: -1.1351

Max Act: 1.0268. Min Act: -0.0001

Data Index: 303246 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.9796. Min Act: -0.0000

Data Index: 527936 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.9200. Min Act: -0.0000

Data Index: 25172 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.8881. Min Act: -0.0000

Data Index: 425061 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.8851. Min Act: -0.0001

Data Index: 1146412 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.9396. Min Act: -0.0000

Data Index: 844698 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.9065. Min Act: -0.0000

Data Index: 687304 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.8394. Min Act: -0.0001

Data Index: 1166879 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.7801. Min Act: -0.0000

Data Index: 709845 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.8559. Min Act: -0.0000

Data Index: 991915 (C4 (Web Text))

Max Activating Token Index: 126