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

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

Neuron 512 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: 3.9381. Min Range: -3.9381

Max Act: 3.9068. Min Act: -0.1700

Data Index: 525481 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.9381. Min Act: -0.1700

Data Index: 504524 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.8443. Min Act: -0.1700

Data Index: 281803 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.8130. Min Act: -0.1700

Data Index: 358887 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.7817. Min Act: -0.1700

Data Index: 277178 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.7817. Min Act: -0.1700

Data Index: 1309203 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.7504. Min Act: -0.1700

Data Index: 1009676 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.7504. Min Act: -0.1700

Data Index: 835845 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.7817. Min Act: -0.1700

Data Index: 960636 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.7504. Min Act: -0.1700

Data Index: 620408 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.7504. Min Act: -0.1700

Data Index: 666425 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.7504. Min Act: -0.1700

Data Index: 669922 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.7504. Min Act: -0.1700

Data Index: 479404 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.7504. Min Act: -0.1700

Data Index: 672002 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.7504. Min Act: -0.1700

Data Index: 131410 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.7191. Min Act: -0.1700

Data Index: 260482 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.7817. Min Act: -0.1700

Data Index: 168717 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.7504. Min Act: -0.1700

Data Index: 1084792 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.7191. Min Act: -0.1700

Data Index: 1237260 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.7191. Min Act: -0.1700

Data Index: 219561 (C4 (Web Text))

Max Activating Token Index: 498