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

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

Neuron 600 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: 5.1111. Min Range: -5.1111

Max Act: 5.1111. Min Act: -0.1700

Data Index: 244070 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 5.1111. Min Range: -5.1111

Max Act: 4.9548. Min Act: -0.1700

Data Index: 1462232 (Python Code)

Max Activating Token Index: 563

Text #2

Max Range: 5.1111. Min Range: -5.1111

Max Act: 5.0017. Min Act: -0.1700

Data Index: 436273 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 5.1111. Min Range: -5.1111

Max Act: 4.9548. Min Act: -0.1700

Data Index: 904416 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 5.1111. Min Range: -5.1111

Max Act: 4.9548. Min Act: -0.1700

Data Index: 1239164 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 5.1111. Min Range: -5.1111

Max Act: 4.9392. Min Act: -0.1700

Data Index: 222411 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 5.1111. Min Range: -5.1111

Max Act: 4.9548. Min Act: -0.1700

Data Index: 729921 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 5.1111. Min Range: -5.1111

Max Act: 4.9236. Min Act: -0.1700

Data Index: 1356114 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 5.1111. Min Range: -5.1111

Max Act: 4.9079. Min Act: -0.1700

Data Index: 53534 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 5.1111. Min Range: -5.1111

Max Act: 4.8923. Min Act: -0.1700

Data Index: 994389 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 5.1111. Min Range: -5.1111

Max Act: 4.9704. Min Act: -0.1700

Data Index: 479750 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 5.1111. Min Range: -5.1111

Max Act: 4.8923. Min Act: -0.1700

Data Index: 636013 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 5.1111. Min Range: -5.1111

Max Act: 4.8923. Min Act: -0.1700

Data Index: 560952 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 5.1111. Min Range: -5.1111

Max Act: 4.8767. Min Act: -0.1700

Data Index: 1189813 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 5.1111. Min Range: -5.1111

Max Act: 4.8298. Min Act: -0.1700

Data Index: 573150 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 5.1111. Min Range: -5.1111

Max Act: 4.8767. Min Act: -0.1700

Data Index: 528312 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 5.1111. Min Range: -5.1111

Max Act: 4.8298. Min Act: -0.1700

Data Index: 709347 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 5.1111. Min Range: -5.1111

Max Act: 4.8923. Min Act: -0.1700

Data Index: 306842 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 5.1111. Min Range: -5.1111

Max Act: 4.8142. Min Act: -0.1700

Data Index: 414153 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 5.1111. Min Range: -5.1111

Max Act: 4.8142. Min Act: -0.1700

Data Index: 509182 (C4 (Web Text))

Max Activating Token Index: 618