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

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

Neuron 1761 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: 5.3744. Min Range: -5.3744

Max Act: 5.3744. Min Act: -0.1700

Data Index: 291740 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 5.3744. Min Range: -5.3744

Max Act: 5.2494. Min Act: -0.1700

Data Index: 847930 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 5.3744. Min Range: -5.3744

Max Act: 5.3119. Min Act: -0.1700

Data Index: 212052 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 5.3744. Min Range: -5.3744

Max Act: 5.3119. Min Act: -0.1700

Data Index: 1226817 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 5.3744. Min Range: -5.3744

Max Act: 5.1244. Min Act: -0.1700

Data Index: 182763 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 5.3744. Min Range: -5.3744

Max Act: 5.1556. Min Act: -0.1700

Data Index: 800521 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 5.3744. Min Range: -5.3744

Max Act: 5.1556. Min Act: -0.1700

Data Index: 308604 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 5.3744. Min Range: -5.3744

Max Act: 5.1556. Min Act: -0.1700

Data Index: 1324668 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 5.3744. Min Range: -5.3744

Max Act: 5.1869. Min Act: -0.1700

Data Index: 127270 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 5.3744. Min Range: -5.3744

Max Act: 5.1244. Min Act: -0.1700

Data Index: 395728 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 5.3744. Min Range: -5.3744

Max Act: 5.1556. Min Act: -0.1700

Data Index: 423285 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 5.3744. Min Range: -5.3744

Max Act: 5.1244. Min Act: -0.1700

Data Index: 1116504 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 5.3744. Min Range: -5.3744

Max Act: 5.1244. Min Act: -0.1700

Data Index: 611146 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 5.3744. Min Range: -5.3744

Max Act: 5.1244. Min Act: -0.1700

Data Index: 619787 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 5.3744. Min Range: -5.3744

Max Act: 5.1244. Min Act: -0.1700

Data Index: 261313 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 5.3744. Min Range: -5.3744

Max Act: 5.1244. Min Act: -0.1700

Data Index: 1006176 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 5.3744. Min Range: -5.3744

Max Act: 5.1244. Min Act: -0.1700

Data Index: 300470 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 5.3744. Min Range: -5.3744

Max Act: 5.0931. Min Act: -0.1700

Data Index: 153625 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 5.3744. Min Range: -5.3744

Max Act: 5.0931. Min Act: -0.1700

Data Index: 266789 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 5.3744. Min Range: -5.3744

Max Act: 5.0931. Min Act: -0.1700

Data Index: 955683 (C4 (Web Text))

Max Activating Token Index: 350