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

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

Neuron 3817 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.2255. Min Act: -0.0000

Data Index: 870384 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1829. Min Act: -0.0000

Data Index: 955588 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1690. Min Act: -0.0000

Data Index: 320119 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1479. Min Act: -0.0000

Data Index: 1176571 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1507. Min Act: -0.0001

Data Index: 1316291 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1394. Min Act: -0.0000

Data Index: 524291 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1201. Min Act: -0.0000

Data Index: 318648 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1209. Min Act: -0.0000

Data Index: 1278940 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1198. Min Act: -0.0000

Data Index: 98844 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1134. Min Act: -0.0000

Data Index: 1280245 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1177. Min Act: -0.0000

Data Index: 60773 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1106. Min Act: -0.0000

Data Index: 1001052 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1129. Min Act: -0.0000

Data Index: 660269 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1119. Min Act: -0.0000

Data Index: 524879 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1138. Min Act: -0.0000

Data Index: 342713 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1057. Min Act: -0.0000

Data Index: 618610 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1035. Min Act: -0.0000

Data Index: 700872 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1059. Min Act: -0.0000

Data Index: 131592 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1063. Min Act: -0.0000

Data Index: 767648 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.0982. Min Act: -0.0000

Data Index: 1077748 (C4 (Web Text))

Max Activating Token Index: 254