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

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

Neuron 83 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: 3.2211. Min Range: -3.2211

Max Act: 3.2211. Min Act: -0.1700

Data Index: 1575339 (Python Code)

Max Activating Token Index: 271

Text #1

Max Range: 3.2211. Min Range: -3.2211

Max Act: 3.2096. Min Act: -0.1700

Data Index: 464037 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 3.2211. Min Range: -3.2211

Max Act: 3.1222. Min Act: -0.1700

Data Index: 469137 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 3.2211. Min Range: -3.2211

Max Act: 3.0899. Min Act: -0.1700

Data Index: 588299 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 3.2211. Min Range: -3.2211

Max Act: 3.0929. Min Act: -0.1700

Data Index: 1408521 (Python Code)

Max Activating Token Index: 279

Text #5

Max Range: 3.2211. Min Range: -3.2211

Max Act: 3.0878. Min Act: -0.1700

Data Index: 1292376 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 3.2211. Min Range: -3.2211

Max Act: 3.0756. Min Act: -0.1700

Data Index: 800406 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 3.2211. Min Range: -3.2211

Max Act: 3.0642. Min Act: -0.1700

Data Index: 706563 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 3.2211. Min Range: -3.2211

Max Act: 3.0554. Min Act: -0.1700

Data Index: 48842 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 3.2211. Min Range: -3.2211

Max Act: 3.0509. Min Act: -0.1700

Data Index: 1045558 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 3.2211. Min Range: -3.2211

Max Act: 3.0559. Min Act: -0.1700

Data Index: 1332995 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 3.2211. Min Range: -3.2211

Max Act: 3.0381. Min Act: -0.1700

Data Index: 1205525 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 3.2211. Min Range: -3.2211

Max Act: 3.0207. Min Act: -0.1700

Data Index: 197973 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 3.2211. Min Range: -3.2211

Max Act: 3.0341. Min Act: -0.1700

Data Index: 860356 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 3.2211. Min Range: -3.2211

Max Act: 3.0004. Min Act: -0.1700

Data Index: 84874 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 3.2211. Min Range: -3.2211

Max Act: 3.0002. Min Act: -0.1700

Data Index: 208257 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 3.2211. Min Range: -3.2211

Max Act: 3.0190. Min Act: -0.1700

Data Index: 1192487 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 3.2211. Min Range: -3.2211

Max Act: 2.9990. Min Act: -0.1700

Data Index: 1120209 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 3.2211. Min Range: -3.2211

Max Act: 3.0095. Min Act: -0.1700

Data Index: 500229 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 3.2211. Min Range: -3.2211

Max Act: 2.9978. Min Act: -0.1700

Data Index: 336522 (C4 (Web Text))

Max Activating Token Index: 810