Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 63 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.9158. Min Range: -3.9158

Max Act: 3.9158. Min Act: -0.1700

Data Index: 288427 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 3.9158. Min Range: -3.9158

Max Act: 3.8376. Min Act: -0.1700

Data Index: 1177394 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 3.9158. Min Range: -3.9158

Max Act: 3.8219. Min Act: -0.1700

Data Index: 483863 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 3.9158. Min Range: -3.9158

Max Act: 3.7906. Min Act: -0.1700

Data Index: 995672 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 3.9158. Min Range: -3.9158

Max Act: 3.8063. Min Act: -0.1700

Data Index: 1081012 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 3.9158. Min Range: -3.9158

Max Act: 3.8063. Min Act: -0.1700

Data Index: 726888 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 3.9158. Min Range: -3.9158

Max Act: 3.7906. Min Act: -0.1700

Data Index: 483994 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 3.9158. Min Range: -3.9158

Max Act: 3.8063. Min Act: -0.1700

Data Index: 687913 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 3.9158. Min Range: -3.9158

Max Act: 3.7750. Min Act: -0.1700

Data Index: 707482 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 3.9158. Min Range: -3.9158

Max Act: 3.7594. Min Act: -0.1700

Data Index: 1341413 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 3.9158. Min Range: -3.9158

Max Act: 3.7281. Min Act: -0.1700

Data Index: 841186 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 3.9158. Min Range: -3.9158

Max Act: 3.7281. Min Act: -0.1700

Data Index: 146082 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 3.9158. Min Range: -3.9158

Max Act: 3.7437. Min Act: -0.1700

Data Index: 384081 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 3.9158. Min Range: -3.9158

Max Act: 3.7594. Min Act: -0.1700

Data Index: 67030 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 3.9158. Min Range: -3.9158

Max Act: 3.7124. Min Act: -0.1700

Data Index: 367532 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 3.9158. Min Range: -3.9158

Max Act: 3.7124. Min Act: -0.1700

Data Index: 773238 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 3.9158. Min Range: -3.9158

Max Act: 3.6811. Min Act: -0.1700

Data Index: 1354812 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 3.9158. Min Range: -3.9158

Max Act: 3.6968. Min Act: -0.1700

Data Index: 565544 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 3.9158. Min Range: -3.9158

Max Act: 3.6968. Min Act: -0.1700

Data Index: 1120767 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 3.9158. Min Range: -3.9158

Max Act: 3.6655. Min Act: -0.1700

Data Index: 723717 (C4 (Web Text))

Max Activating Token Index: 599