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

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

Neuron 3302 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1394. Min Act: -0.0002

Data Index: 1229623 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1387. Min Act: -0.0002

Data Index: 790256 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1265. Min Act: -0.0002

Data Index: 206522 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1221. Min Act: -0.0002

Data Index: 1120771 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1213. Min Act: -0.0002

Data Index: 905562 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1150. Min Act: -0.0002

Data Index: 121360 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1110. Min Act: -0.0002

Data Index: 1302077 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1125. Min Act: -0.0002

Data Index: 523578 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1144. Min Act: -0.0003

Data Index: 1166078 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1113. Min Act: -0.0002

Data Index: 222468 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1094. Min Act: -0.0002

Data Index: 751191 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1026. Min Act: -0.0002

Data Index: 1249699 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1006. Min Act: -0.0002

Data Index: 414460 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1030. Min Act: -0.0003

Data Index: 808509 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0978. Min Act: -0.0002

Data Index: 36856 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0979. Min Act: -0.0002

Data Index: 374377 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0991. Min Act: -0.0002

Data Index: 74206 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1000. Min Act: -0.0002

Data Index: 135824 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0972. Min Act: -0.0002

Data Index: 757622 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0989. Min Act: -0.0002

Data Index: 175896 (C4 (Web Text))

Max Activating Token Index: 406