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

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

Neuron 234 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6312. Min Range: -5.6312

Max Act: 5.6312. Min Act: -0.1700

Data Index: 1269255 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 5.6312. Min Range: -5.6312

Max Act: 5.6000. Min Act: -0.1700

Data Index: 504973 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 5.6312. Min Range: -5.6312

Max Act: 5.5062. Min Act: -0.1700

Data Index: 1299000 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 5.6312. Min Range: -5.6312

Max Act: 5.5062. Min Act: -0.1700

Data Index: 291848 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 5.6312. Min Range: -5.6312

Max Act: 5.5687. Min Act: -0.1699

Data Index: 1343982 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 5.6312. Min Range: -5.6312

Max Act: 5.5375. Min Act: -0.1700

Data Index: 446612 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 5.6312. Min Range: -5.6312

Max Act: 5.4750. Min Act: -0.1700

Data Index: 479612 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 5.6312. Min Range: -5.6312

Max Act: 5.3500. Min Act: -0.1700

Data Index: 224782 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 5.6312. Min Range: -5.6312

Max Act: 5.3812. Min Act: -0.1700

Data Index: 259861 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 5.6312. Min Range: -5.6312

Max Act: 5.4437. Min Act: -0.1700

Data Index: 1277890 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 5.6312. Min Range: -5.6312

Max Act: 5.2875. Min Act: -0.1700

Data Index: 553350 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 5.6312. Min Range: -5.6312

Max Act: 5.3500. Min Act: -0.1700

Data Index: 594253 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 5.6312. Min Range: -5.6312

Max Act: 5.2875. Min Act: -0.1700

Data Index: 704954 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 5.6312. Min Range: -5.6312

Max Act: 5.3187. Min Act: -0.1700

Data Index: 121349 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 5.6312. Min Range: -5.6312

Max Act: 5.2875. Min Act: -0.1700

Data Index: 332551 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 5.6312. Min Range: -5.6312

Max Act: 5.2875. Min Act: -0.1700

Data Index: 870811 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 5.6312. Min Range: -5.6312

Max Act: 5.1312. Min Act: -0.1700

Data Index: 900685 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 5.6312. Min Range: -5.6312

Max Act: 5.3187. Min Act: -0.1700

Data Index: 808484 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 5.6312. Min Range: -5.6312

Max Act: 5.1625. Min Act: -0.1700

Data Index: 261275 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 5.6312. Min Range: -5.6312

Max Act: 5.2250. Min Act: -0.1700

Data Index: 266145 (C4 (Web Text))

Max Activating Token Index: 951