Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 364 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.0396. Min Range: -5.0396

Max Act: 5.0396. Min Act: -0.1700

Data Index: 849024 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 5.0396. Min Range: -5.0396

Max Act: 4.7584. Min Act: -0.1700

Data Index: 971981 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 5.0396. Min Range: -5.0396

Max Act: 4.7896. Min Act: -0.1700

Data Index: 687350 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 5.0396. Min Range: -5.0396

Max Act: 4.7896. Min Act: -0.1699

Data Index: 121050 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 5.0396. Min Range: -5.0396

Max Act: 4.7584. Min Act: -0.1700

Data Index: 825094 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 5.0396. Min Range: -5.0396

Max Act: 4.7271. Min Act: -0.1692

Data Index: 426012 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 5.0396. Min Range: -5.0396

Max Act: 4.7271. Min Act: -0.1700

Data Index: 918054 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 5.0396. Min Range: -5.0396

Max Act: 4.6959. Min Act: -0.1700

Data Index: 427437 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 5.0396. Min Range: -5.0396

Max Act: 4.6334. Min Act: -0.1700

Data Index: 958623 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 5.0396. Min Range: -5.0396

Max Act: 4.6646. Min Act: -0.1698

Data Index: 164192 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 5.0396. Min Range: -5.0396

Max Act: 4.6646. Min Act: -0.1700

Data Index: 340901 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 5.0396. Min Range: -5.0396

Max Act: 4.6021. Min Act: -0.1700

Data Index: 718379 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 5.0396. Min Range: -5.0396

Max Act: 4.5709. Min Act: -0.1700

Data Index: 412946 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 5.0396. Min Range: -5.0396

Max Act: 4.5709. Min Act: -0.1698

Data Index: 971055 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 5.0396. Min Range: -5.0396

Max Act: 4.6021. Min Act: -0.1699

Data Index: 373822 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 5.0396. Min Range: -5.0396

Max Act: 4.5396. Min Act: -0.1700

Data Index: 928746 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 5.0396. Min Range: -5.0396

Max Act: 4.5396. Min Act: -0.1700

Data Index: 1169639 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 5.0396. Min Range: -5.0396

Max Act: 4.5083. Min Act: -0.1700

Data Index: 516226 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 5.0396. Min Range: -5.0396

Max Act: 4.5396. Min Act: -0.1700

Data Index: 1179353 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 5.0396. Min Range: -5.0396

Max Act: 4.5709. Min Act: -0.1700

Data Index: 371199 (C4 (Web Text))

Max Activating Token Index: 17