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

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

Neuron 78 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7810. Min Range: -3.7810

Max Act: 3.7497. Min Act: -0.1700

Data Index: 457880 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 3.7810. Min Range: -3.7810

Max Act: 3.7810. Min Act: -0.1700

Data Index: 1273531 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 3.7810. Min Range: -3.7810

Max Act: 3.7497. Min Act: -0.1700

Data Index: 1350725 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 3.7810. Min Range: -3.7810

Max Act: 3.6871. Min Act: -0.1700

Data Index: 951058 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 3.7810. Min Range: -3.7810

Max Act: 3.7184. Min Act: -0.1700

Data Index: 710725 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 3.7810. Min Range: -3.7810

Max Act: 3.6871. Min Act: -0.1700

Data Index: 1339841 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 3.7810. Min Range: -3.7810

Max Act: 3.7184. Min Act: -0.1700

Data Index: 590679 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 3.7810. Min Range: -3.7810

Max Act: 3.6871. Min Act: -0.1700

Data Index: 27660 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 3.7810. Min Range: -3.7810

Max Act: 3.6558. Min Act: -0.1700

Data Index: 981087 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 3.7810. Min Range: -3.7810

Max Act: 3.6245. Min Act: -0.1699

Data Index: 422249 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 3.7810. Min Range: -3.7810

Max Act: 3.6245. Min Act: -0.1700

Data Index: 365377 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 3.7810. Min Range: -3.7810

Max Act: 3.5932. Min Act: -0.1700

Data Index: 1016507 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 3.7810. Min Range: -3.7810

Max Act: 3.5932. Min Act: -0.1699

Data Index: 640061 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 3.7810. Min Range: -3.7810

Max Act: 3.5305. Min Act: -0.1699

Data Index: 158969 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 3.7810. Min Range: -3.7810

Max Act: 3.5619. Min Act: -0.1700

Data Index: 758016 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 3.7810. Min Range: -3.7810

Max Act: 3.5619. Min Act: -0.1699

Data Index: 87603 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 3.7810. Min Range: -3.7810

Max Act: 3.5305. Min Act: -0.1699

Data Index: 493392 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 3.7810. Min Range: -3.7810

Max Act: 3.5305. Min Act: -0.1700

Data Index: 594874 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 3.7810. Min Range: -3.7810

Max Act: 3.5619. Min Act: -0.1700

Data Index: 933738 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 3.7810. Min Range: -3.7810

Max Act: 3.4992. Min Act: -0.1700

Data Index: 443061 (C4 (Web Text))

Max Activating Token Index: 228