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

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

Neuron 1680 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: 5.6612. Min Range: -5.6612

Max Act: 5.5987. Min Act: -0.1700

Data Index: 944096 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 5.6612. Min Range: -5.6612

Max Act: 5.6300. Min Act: -0.1700

Data Index: 107292 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 5.6612. Min Range: -5.6612

Max Act: 5.6612. Min Act: -0.1700

Data Index: 316113 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 5.6612. Min Range: -5.6612

Max Act: 5.5675. Min Act: -0.1700

Data Index: 1257624 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 5.6612. Min Range: -5.6612

Max Act: 5.6300. Min Act: -0.1700

Data Index: 250390 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 5.6612. Min Range: -5.6612

Max Act: 5.4737. Min Act: -0.1700

Data Index: 677723 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 5.6612. Min Range: -5.6612

Max Act: 5.5362. Min Act: -0.1700

Data Index: 1000660 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 5.6612. Min Range: -5.6612

Max Act: 5.4737. Min Act: -0.1700

Data Index: 733899 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 5.6612. Min Range: -5.6612

Max Act: 5.4425. Min Act: -0.1700

Data Index: 389447 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 5.6612. Min Range: -5.6612

Max Act: 5.4112. Min Act: -0.1700

Data Index: 189918 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 5.6612. Min Range: -5.6612

Max Act: 5.4425. Min Act: -0.1700

Data Index: 115795 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 5.6612. Min Range: -5.6612

Max Act: 5.4112. Min Act: -0.1700

Data Index: 1023725 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 5.6612. Min Range: -5.6612

Max Act: 5.4112. Min Act: -0.1700

Data Index: 641779 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 5.6612. Min Range: -5.6612

Max Act: 5.4112. Min Act: -0.1700

Data Index: 1328423 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 5.6612. Min Range: -5.6612

Max Act: 5.4425. Min Act: -0.1700

Data Index: 155469 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 5.6612. Min Range: -5.6612

Max Act: 5.4112. Min Act: -0.1700

Data Index: 176874 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 5.6612. Min Range: -5.6612

Max Act: 5.3487. Min Act: -0.1700

Data Index: 958336 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 5.6612. Min Range: -5.6612

Max Act: 5.3800. Min Act: -0.1700

Data Index: 187511 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 5.6612. Min Range: -5.6612

Max Act: 5.4425. Min Act: -0.1700

Data Index: 432702 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 5.6612. Min Range: -5.6612

Max Act: 5.3800. Min Act: -0.1699

Data Index: 643878 (C4 (Web Text))

Max Activating Token Index: 108