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

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

Neuron 1241 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: 5.4452. Min Range: -5.4452

Max Act: 5.4452. Min Act: -0.1700

Data Index: 892188 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 5.4452. Min Range: -5.4452

Max Act: 5.2265. Min Act: -0.1700

Data Index: 1002693 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 5.4452. Min Range: -5.4452

Max Act: 5.1015. Min Act: -0.1700

Data Index: 64276 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 5.4452. Min Range: -5.4452

Max Act: 4.9765. Min Act: -0.1700

Data Index: 873794 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 5.4452. Min Range: -5.4452

Max Act: 5.0077. Min Act: -0.1700

Data Index: 198112 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 5.4452. Min Range: -5.4452

Max Act: 4.9452. Min Act: -0.1700

Data Index: 544864 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 5.4452. Min Range: -5.4452

Max Act: 4.9765. Min Act: -0.1700

Data Index: 912592 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 5.4452. Min Range: -5.4452

Max Act: 4.9452. Min Act: -0.1700

Data Index: 1317008 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 5.4452. Min Range: -5.4452

Max Act: 4.9140. Min Act: -0.1700

Data Index: 1143151 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 5.4452. Min Range: -5.4452

Max Act: 4.8984. Min Act: -0.1700

Data Index: 1002259 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 5.4452. Min Range: -5.4452

Max Act: 4.9140. Min Act: -0.1700

Data Index: 961969 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 5.4452. Min Range: -5.4452

Max Act: 4.8671. Min Act: -0.1699

Data Index: 613550 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 5.4452. Min Range: -5.4452

Max Act: 4.8046. Min Act: -0.1700

Data Index: 30110 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 5.4452. Min Range: -5.4452

Max Act: 4.8515. Min Act: -0.1700

Data Index: 1094684 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 5.4452. Min Range: -5.4452

Max Act: 4.8359. Min Act: -0.1700

Data Index: 965613 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 5.4452. Min Range: -5.4452

Max Act: 4.8202. Min Act: -0.1700

Data Index: 46407 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 5.4452. Min Range: -5.4452

Max Act: 4.7890. Min Act: -0.1699

Data Index: 1031124 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 5.4452. Min Range: -5.4452

Max Act: 4.8046. Min Act: -0.1700

Data Index: 870781 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 5.4452. Min Range: -5.4452

Max Act: 4.7890. Min Act: -0.1700

Data Index: 1304207 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 5.4452. Min Range: -5.4452

Max Act: 4.7577. Min Act: -0.1700

Data Index: 188963 (C4 (Web Text))

Max Activating Token Index: 700