Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1926 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.0172. Min Range: -4.0172

Max Act: 4.0172. Min Act: -0.1700

Data Index: 502214 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.9003. Min Act: -0.1699

Data Index: 200507 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.7747. Min Act: -0.1700

Data Index: 406430 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.7904. Min Act: -0.1700

Data Index: 1157660 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.6862. Min Act: -0.1700

Data Index: 312672 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.6742. Min Act: -0.1700

Data Index: 279648 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.6626. Min Act: -0.1700

Data Index: 229330 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.6357. Min Act: -0.1700

Data Index: 156747 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.6132. Min Act: -0.1700

Data Index: 1230314 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.6381. Min Act: -0.1700

Data Index: 496807 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.6326. Min Act: -0.1700

Data Index: 1109217 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.6260. Min Act: -0.1700

Data Index: 1269998 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.6216. Min Act: -0.1700

Data Index: 203726 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.6220. Min Act: -0.1700

Data Index: 932035 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.6096. Min Act: -0.1700

Data Index: 889227 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.6210. Min Act: -0.1700

Data Index: 496037 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.6025. Min Act: -0.1700

Data Index: 405587 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.5996. Min Act: -0.1700

Data Index: 726414 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.5927. Min Act: -0.1693

Data Index: 701666 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.5964. Min Act: -0.1700

Data Index: 1212722 (C4 (Web Text))

Max Activating Token Index: 833