Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1686 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 7.4267. Min Range: -7.4267

Max Act: 7.4267. Min Act: -0.1700

Data Index: 216959 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 7.4267. Min Range: -7.4267

Max Act: 7.1767. Min Act: -0.1700

Data Index: 1252024 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 7.4267. Min Range: -7.4267

Max Act: 7.1767. Min Act: -0.1699

Data Index: 900849 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 7.4267. Min Range: -7.4267

Max Act: 7.0517. Min Act: -0.1700

Data Index: 722214 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 7.4267. Min Range: -7.4267

Max Act: 7.0205. Min Act: -0.1700

Data Index: 267494 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 7.4267. Min Range: -7.4267

Max Act: 7.0830. Min Act: -0.1700

Data Index: 985290 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 7.4267. Min Range: -7.4267

Max Act: 7.0517. Min Act: -0.1700

Data Index: 425009 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 7.4267. Min Range: -7.4267

Max Act: 7.0517. Min Act: -0.1700

Data Index: 461204 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 7.4267. Min Range: -7.4267

Max Act: 7.0205. Min Act: -0.1700

Data Index: 1160578 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 7.4267. Min Range: -7.4267

Max Act: 7.0517. Min Act: -0.1697

Data Index: 807549 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 7.4267. Min Range: -7.4267

Max Act: 6.9892. Min Act: -0.1700

Data Index: 261010 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 7.4267. Min Range: -7.4267

Max Act: 7.0205. Min Act: -0.1700

Data Index: 343485 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 7.4267. Min Range: -7.4267

Max Act: 7.0205. Min Act: -0.1700

Data Index: 694747 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 7.4267. Min Range: -7.4267

Max Act: 7.0517. Min Act: -0.1699

Data Index: 213887 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 7.4267. Min Range: -7.4267

Max Act: 7.0205. Min Act: -0.1696

Data Index: 1033261 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 7.4267. Min Range: -7.4267

Max Act: 7.0205. Min Act: -0.1700

Data Index: 33028 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 7.4267. Min Range: -7.4267

Max Act: 6.9580. Min Act: -0.1700

Data Index: 1311484 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 7.4267. Min Range: -7.4267

Max Act: 7.0205. Min Act: -0.1700

Data Index: 1044223 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 7.4267. Min Range: -7.4267

Max Act: 6.8642. Min Act: -0.1700

Data Index: 493447 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 7.4267. Min Range: -7.4267

Max Act: 6.9580. Min Act: -0.1700

Data Index: 524120 (C4 (Web Text))

Max Activating Token Index: 379