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

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

Neuron 660 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0825. Min Range: -1.0825

Max Act: 1.0825. Min Act: -0.0000

Data Index: 1225114 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.9131. Min Act: -0.0000

Data Index: 987725 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.9425. Min Act: -0.0000

Data Index: 809180 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.8367. Min Act: -0.0000

Data Index: 957129 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.7976. Min Act: -0.0000

Data Index: 1114137 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.7872. Min Act: -0.0000

Data Index: 1153372 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.8039. Min Act: -0.0000

Data Index: 564324 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.7718. Min Act: -0.0000

Data Index: 242040 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.7296. Min Act: -0.0000

Data Index: 766080 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.6893. Min Act: -0.0000

Data Index: 684262 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.6796. Min Act: -0.0000

Data Index: 593971 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.6916. Min Act: -0.0000

Data Index: 818929 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.7003. Min Act: -0.0000

Data Index: 286872 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.7050. Min Act: -0.0000

Data Index: 960802 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.6754. Min Act: -0.0000

Data Index: 1044298 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.6932. Min Act: -0.0000

Data Index: 1247588 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1136037 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.6865. Min Act: -0.0000

Data Index: 1327764 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1069016 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1001429 (C4 (Web Text))

Max Activating Token Index: 489