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

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

Neuron 35 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9145. Min Range: -3.9145

Max Act: 3.9145. Min Act: -0.1700

Data Index: 753738 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 3.9145. Min Range: -3.9145

Max Act: 3.7894. Min Act: -0.1700

Data Index: 825165 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 3.9145. Min Range: -3.9145

Max Act: 3.8207. Min Act: -0.1700

Data Index: 799603 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 3.9145. Min Range: -3.9145

Max Act: 3.7268. Min Act: -0.1700

Data Index: 988915 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 3.9145. Min Range: -3.9145

Max Act: 3.7894. Min Act: -0.1700

Data Index: 965506 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 3.9145. Min Range: -3.9145

Max Act: 3.8207. Min Act: -0.1700

Data Index: 792931 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 3.9145. Min Range: -3.9145

Max Act: 3.8207. Min Act: -0.1700

Data Index: 1314164 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 3.9145. Min Range: -3.9145

Max Act: 3.7894. Min Act: -0.1700

Data Index: 361402 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 3.9145. Min Range: -3.9145

Max Act: 3.7425. Min Act: -0.1700

Data Index: 640426 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 3.9145. Min Range: -3.9145

Max Act: 3.7894. Min Act: -0.1700

Data Index: 938221 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 3.9145. Min Range: -3.9145

Max Act: 3.7581. Min Act: -0.1700

Data Index: 689835 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 3.9145. Min Range: -3.9145

Max Act: 3.6955. Min Act: -0.1700

Data Index: 360547 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 3.9145. Min Range: -3.9145

Max Act: 3.7425. Min Act: -0.1700

Data Index: 450675 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 3.9145. Min Range: -3.9145

Max Act: 3.7581. Min Act: -0.1700

Data Index: 119027 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 3.9145. Min Range: -3.9145

Max Act: 3.7581. Min Act: -0.1700

Data Index: 672855 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 3.9145. Min Range: -3.9145

Max Act: 3.7581. Min Act: -0.1700

Data Index: 229801 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 3.9145. Min Range: -3.9145

Max Act: 3.6955. Min Act: -0.1700

Data Index: 704333 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 3.9145. Min Range: -3.9145

Max Act: 3.7581. Min Act: -0.1700

Data Index: 465854 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 3.9145. Min Range: -3.9145

Max Act: 3.7425. Min Act: -0.1700

Data Index: 480633 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 3.9145. Min Range: -3.9145

Max Act: 3.6955. Min Act: -0.1700

Data Index: 95241 (C4 (Web Text))

Max Activating Token Index: 566