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

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

Neuron 54 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0338. Min Range: -5.0338

Max Act: 5.0026. Min Act: -0.1700

Data Index: 1136954 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 5.0338. Min Range: -5.0338

Max Act: 5.0338. Min Act: -0.1700

Data Index: 362708 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 5.0338. Min Range: -5.0338

Max Act: 5.0338. Min Act: -0.1700

Data Index: 837973 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.9713. Min Act: -0.1700

Data Index: 869600 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 5.0338. Min Range: -5.0338

Max Act: 5.0338. Min Act: -0.1700

Data Index: 905803 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 5.0338. Min Range: -5.0338

Max Act: 5.0026. Min Act: -0.1700

Data Index: 1001284 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.9713. Min Act: -0.1700

Data Index: 1033877 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 5.0338. Min Range: -5.0338

Max Act: 5.0338. Min Act: -0.1700

Data Index: 1083797 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.9713. Min Act: -0.1700

Data Index: 757811 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 5.0338. Min Range: -5.0338

Max Act: 5.0026. Min Act: -0.1700

Data Index: 619578 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.9713. Min Act: -0.1700

Data Index: 297313 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 5.0338. Min Range: -5.0338

Max Act: 5.0026. Min Act: -0.1700

Data Index: 689452 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.9088. Min Act: -0.1700

Data Index: 317800 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.9401. Min Act: -0.1700

Data Index: 592615 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.8463. Min Act: -0.1700

Data Index: 1192745 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.9088. Min Act: -0.1700

Data Index: 149062 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.9401. Min Act: -0.1700

Data Index: 929012 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.8776. Min Act: -0.1700

Data Index: 670378 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.8463. Min Act: -0.1700

Data Index: 62302 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 5.0338. Min Range: -5.0338

Max Act: 4.9088. Min Act: -0.1700

Data Index: 240359 (C4 (Web Text))

Max Activating Token Index: 520