Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5306 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0274. Min Range: -1.0274

Max Act: 1.0274. Min Act: -0.0000

Data Index: 1077096 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.9672. Min Act: -0.0000

Data Index: 141932 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.9479. Min Act: -0.0000

Data Index: 772850 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.9250. Min Act: -0.0000

Data Index: 1135726 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.8974. Min Act: -0.0000

Data Index: 367820 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.9285. Min Act: -0.0000

Data Index: 219701 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.8801. Min Act: -0.0000

Data Index: 16158 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.9009. Min Act: -0.0000

Data Index: 1080889 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.8453. Min Act: -0.0000

Data Index: 55610 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.8537. Min Act: -0.0000

Data Index: 351330 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.7928. Min Act: -0.0000

Data Index: 345720 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.7914. Min Act: -0.0000

Data Index: 314452 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.7366. Min Act: -0.0000

Data Index: 810844 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.7330. Min Act: -0.0000

Data Index: 148831 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.7717. Min Act: -0.0000

Data Index: 1143936 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.7708. Min Act: -0.0000

Data Index: 1155700 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.7628. Min Act: -0.0000

Data Index: 1194673 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.7625. Min Act: -0.0000

Data Index: 432916 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.7637. Min Act: -0.0000

Data Index: 421748 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1177930 (C4 (Web Text))

Max Activating Token Index: 204