Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 181 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.5417. Min Act: -0.1700

Data Index: 68907 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.4163. Min Act: -0.1700

Data Index: 94029 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.4477. Min Act: -0.1700

Data Index: 839082 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.4634. Min Act: -0.1700

Data Index: 110055 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.3222. Min Act: -0.1700

Data Index: 655450 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.4477. Min Act: -0.1700

Data Index: 1179925 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.3536. Min Act: -0.1700

Data Index: 470862 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.3222. Min Act: -0.1700

Data Index: 422789 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.3222. Min Act: -0.1700

Data Index: 744245 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.3850. Min Act: -0.1700

Data Index: 299398 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.3222. Min Act: -0.1700

Data Index: 1216663 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.2594. Min Act: -0.1700

Data Index: 607694 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.3065. Min Act: -0.1700

Data Index: 334405 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.2436. Min Act: -0.1700

Data Index: 62355 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.2908. Min Act: -0.1700

Data Index: 1212808 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.2122. Min Act: -0.1700

Data Index: 1087613 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.1650. Min Act: -0.1700

Data Index: 1200881 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.3693. Min Act: -0.1700

Data Index: 603778 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.2908. Min Act: -0.1700

Data Index: 396085 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 3.5417. Min Range: -3.5417

Max Act: 3.2594. Min Act: -0.1700

Data Index: 344931 (C4 (Web Text))

Max Activating Token Index: 809