Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1675 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8626. Min Range: -3.8626

Max Act: 3.8626. Min Act: -0.1700

Data Index: 735829 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 3.8626. Min Range: -3.8626

Max Act: 3.8314. Min Act: -0.1700

Data Index: 532005 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 3.8626. Min Range: -3.8626

Max Act: 3.7688. Min Act: -0.1700

Data Index: 778292 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 3.8626. Min Range: -3.8626

Max Act: 3.7062. Min Act: -0.1700

Data Index: 198075 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 3.8626. Min Range: -3.8626

Max Act: 3.7062. Min Act: -0.1700

Data Index: 216765 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 3.8626. Min Range: -3.8626

Max Act: 3.7375. Min Act: -0.1700

Data Index: 1052923 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 3.8626. Min Range: -3.8626

Max Act: 3.7062. Min Act: -0.1700

Data Index: 1106644 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 3.8626. Min Range: -3.8626

Max Act: 3.7062. Min Act: -0.1700

Data Index: 1058424 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 3.8626. Min Range: -3.8626

Max Act: 3.7062. Min Act: -0.1700

Data Index: 1133451 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 3.8626. Min Range: -3.8626

Max Act: 3.7062. Min Act: -0.1700

Data Index: 1208380 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 3.8626. Min Range: -3.8626

Max Act: 3.7062. Min Act: -0.1700

Data Index: 731542 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.8626. Min Range: -3.8626

Max Act: 3.7062. Min Act: -0.1700

Data Index: 241896 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 3.8626. Min Range: -3.8626

Max Act: 3.6749. Min Act: -0.1700

Data Index: 49256 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 3.8626. Min Range: -3.8626

Max Act: 3.7062. Min Act: -0.1700

Data Index: 26792 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 3.8626. Min Range: -3.8626

Max Act: 3.6436. Min Act: -0.1700

Data Index: 237595 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 3.8626. Min Range: -3.8626

Max Act: 3.6436. Min Act: -0.1700

Data Index: 845764 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 3.8626. Min Range: -3.8626

Max Act: 3.6749. Min Act: -0.1700

Data Index: 1070046 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 3.8626. Min Range: -3.8626

Max Act: 3.6593. Min Act: -0.1700

Data Index: 609386 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 3.8626. Min Range: -3.8626

Max Act: 3.6436. Min Act: -0.1700

Data Index: 697724 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 3.8626. Min Range: -3.8626

Max Act: 3.6436. Min Act: -0.1700

Data Index: 693610 (C4 (Web Text))

Max Activating Token Index: 456