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

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

Neuron 3566 in Layer 0

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: 0.0224. Min Range: -0.0224

Max Act: 0.0223. Min Act: -0.0001

Data Index: 1071288 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0224. Min Act: -0.0001

Data Index: 495457 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0219. Min Act: -0.0001

Data Index: 771123 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0219. Min Act: -0.0001

Data Index: 626454 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0214. Min Act: -0.0001

Data Index: 1331070 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0206. Min Act: -0.0001

Data Index: 457255 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0212. Min Act: -0.0001

Data Index: 26057 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0207. Min Act: -0.0001

Data Index: 1033898 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0205. Min Act: -0.0001

Data Index: 1238222 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0207. Min Act: -0.0001

Data Index: 375426 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0207. Min Act: -0.0001

Data Index: 117853 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0204. Min Act: -0.0001

Data Index: 865662 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0206. Min Act: -0.0001

Data Index: 23786 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0203. Min Act: -0.0001

Data Index: 813927 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0203. Min Act: -0.0001

Data Index: 1261295 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0203. Min Act: -0.0001

Data Index: 586764 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0202. Min Act: -0.0001

Data Index: 432840 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0199. Min Act: -0.0001

Data Index: 372556 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0200. Min Act: -0.0001

Data Index: 1147638 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0200. Min Act: -0.0001

Data Index: 128926 (C4 (Web Text))

Max Activating Token Index: 178