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

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

Neuron 1490 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: 5.6309. Min Range: -5.6309

Max Act: 5.6309. Min Act: -0.1700

Data Index: 951247 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 5.6309. Min Range: -5.6309

Max Act: 5.5372. Min Act: -0.1700

Data Index: 586724 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 5.6309. Min Range: -5.6309

Max Act: 5.5684. Min Act: -0.1700

Data Index: 112941 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 5.6309. Min Range: -5.6309

Max Act: 5.5059. Min Act: -0.1700

Data Index: 823478 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 5.6309. Min Range: -5.6309

Max Act: 5.4747. Min Act: -0.1700

Data Index: 1267109 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 5.6309. Min Range: -5.6309

Max Act: 5.4747. Min Act: -0.1700

Data Index: 968657 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 5.6309. Min Range: -5.6309

Max Act: 5.4747. Min Act: -0.1700

Data Index: 1057743 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 5.6309. Min Range: -5.6309

Max Act: 5.4434. Min Act: -0.1700

Data Index: 781176 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 5.6309. Min Range: -5.6309

Max Act: 5.4747. Min Act: -0.1700

Data Index: 709596 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 5.6309. Min Range: -5.6309

Max Act: 5.3809. Min Act: -0.1700

Data Index: 1161535 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 5.6309. Min Range: -5.6309

Max Act: 5.4122. Min Act: -0.1700

Data Index: 563906 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 5.6309. Min Range: -5.6309

Max Act: 5.4434. Min Act: -0.1700

Data Index: 1287996 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 5.6309. Min Range: -5.6309

Max Act: 5.4434. Min Act: -0.1700

Data Index: 632535 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 5.6309. Min Range: -5.6309

Max Act: 5.4122. Min Act: -0.1700

Data Index: 19849 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 5.6309. Min Range: -5.6309

Max Act: 5.4122. Min Act: -0.1700

Data Index: 885905 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 5.6309. Min Range: -5.6309

Max Act: 5.4122. Min Act: -0.1700

Data Index: 851576 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 5.6309. Min Range: -5.6309

Max Act: 5.4434. Min Act: -0.1700

Data Index: 1125128 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 5.6309. Min Range: -5.6309

Max Act: 5.4122. Min Act: -0.1700

Data Index: 220048 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 5.6309. Min Range: -5.6309

Max Act: 5.3497. Min Act: -0.1700

Data Index: 753412 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 5.6309. Min Range: -5.6309

Max Act: 5.4122. Min Act: -0.1700

Data Index: 886035 (C4 (Web Text))

Max Activating Token Index: 738