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

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

Neuron 1398 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0099. Min Range: -5.0099

Max Act: 5.0099. Min Act: -0.1700

Data Index: 767696 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 5.0099. Min Range: -5.0099

Max Act: 4.9787. Min Act: -0.1700

Data Index: 565916 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 5.0099. Min Range: -5.0099

Max Act: 4.9787. Min Act: -0.1700

Data Index: 1232627 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 5.0099. Min Range: -5.0099

Max Act: 4.9474. Min Act: -0.1700

Data Index: 172532 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 5.0099. Min Range: -5.0099

Max Act: 5.0099. Min Act: -0.1700

Data Index: 733412 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 5.0099. Min Range: -5.0099

Max Act: 4.9162. Min Act: -0.1700

Data Index: 751360 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 5.0099. Min Range: -5.0099

Max Act: 4.8537. Min Act: -0.1700

Data Index: 302013 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 5.0099. Min Range: -5.0099

Max Act: 4.8224. Min Act: -0.1700

Data Index: 88325 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 5.0099. Min Range: -5.0099

Max Act: 4.8537. Min Act: -0.1700

Data Index: 1334352 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 5.0099. Min Range: -5.0099

Max Act: 4.7912. Min Act: -0.1700

Data Index: 643404 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 5.0099. Min Range: -5.0099

Max Act: 4.8537. Min Act: -0.1700

Data Index: 703753 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 5.0099. Min Range: -5.0099

Max Act: 4.8224. Min Act: -0.1700

Data Index: 378225 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 5.0099. Min Range: -5.0099

Max Act: 4.8537. Min Act: -0.1700

Data Index: 1152907 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 5.0099. Min Range: -5.0099

Max Act: 4.7912. Min Act: -0.1700

Data Index: 339416 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 5.0099. Min Range: -5.0099

Max Act: 4.7599. Min Act: -0.1700

Data Index: 1315460 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 5.0099. Min Range: -5.0099

Max Act: 4.7287. Min Act: -0.1700

Data Index: 218661 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 5.0099. Min Range: -5.0099

Max Act: 4.7287. Min Act: -0.1700

Data Index: 729326 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 5.0099. Min Range: -5.0099

Max Act: 4.7287. Min Act: -0.1700

Data Index: 1023789 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 5.0099. Min Range: -5.0099

Max Act: 4.7287. Min Act: -0.1700

Data Index: 922688 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 5.0099. Min Range: -5.0099

Max Act: 4.7912. Min Act: -0.1700

Data Index: 764177 (C4 (Web Text))

Max Activating Token Index: 609