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

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

Neuron 933 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: 5.8501. Min Range: -5.8501

Max Act: 5.8501. Min Act: -0.1699

Data Index: 1109012 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 5.8501. Min Range: -5.8501

Max Act: 5.5689. Min Act: -0.1700

Data Index: 985214 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 5.8501. Min Range: -5.8501

Max Act: 5.6314. Min Act: -0.1700

Data Index: 573389 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 5.8501. Min Range: -5.8501

Max Act: 5.6001. Min Act: -0.1700

Data Index: 212625 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 5.8501. Min Range: -5.8501

Max Act: 5.6001. Min Act: -0.1700

Data Index: 679611 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 5.8501. Min Range: -5.8501

Max Act: 5.5689. Min Act: -0.1700

Data Index: 1040207 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 5.8501. Min Range: -5.8501

Max Act: 5.5689. Min Act: -0.1700

Data Index: 925794 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 5.8501. Min Range: -5.8501

Max Act: 5.5376. Min Act: -0.1700

Data Index: 616070 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 5.8501. Min Range: -5.8501

Max Act: 5.5689. Min Act: -0.1700

Data Index: 125157 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 5.8501. Min Range: -5.8501

Max Act: 5.5689. Min Act: -0.1700

Data Index: 161666 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 5.8501. Min Range: -5.8501

Max Act: 5.5376. Min Act: -0.1700

Data Index: 599110 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 5.8501. Min Range: -5.8501

Max Act: 5.5376. Min Act: -0.1699

Data Index: 313601 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 5.8501. Min Range: -5.8501

Max Act: 5.5689. Min Act: -0.1700

Data Index: 1327325 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 5.8501. Min Range: -5.8501

Max Act: 5.5376. Min Act: -0.1700

Data Index: 1232907 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 5.8501. Min Range: -5.8501

Max Act: 5.5376. Min Act: -0.1700

Data Index: 859863 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 5.8501. Min Range: -5.8501

Max Act: 5.5376. Min Act: -0.1699

Data Index: 856462 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 5.8501. Min Range: -5.8501

Max Act: 5.4439. Min Act: -0.1699

Data Index: 601234 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 5.8501. Min Range: -5.8501

Max Act: 5.4751. Min Act: -0.1698

Data Index: 961715 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 5.8501. Min Range: -5.8501

Max Act: 5.4126. Min Act: -0.1700

Data Index: 376886 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 5.8501. Min Range: -5.8501

Max Act: 5.4751. Min Act: -0.1700

Data Index: 783201 (C4 (Web Text))

Max Activating Token Index: 248