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

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

Neuron 222 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.1271. Min Range: -3.1271

Max Act: 3.1113. Min Act: -0.1700

Data Index: 23978 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 3.1271. Min Range: -3.1271

Max Act: 3.1113. Min Act: -0.1700

Data Index: 278737 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 3.1271. Min Range: -3.1271

Max Act: 3.0955. Min Act: -0.1700

Data Index: 1049249 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 3.1271. Min Range: -3.1271

Max Act: 3.1113. Min Act: -0.1700

Data Index: 948587 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 3.1271. Min Range: -3.1271

Max Act: 3.1113. Min Act: -0.1700

Data Index: 936601 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 3.1271. Min Range: -3.1271

Max Act: 3.1113. Min Act: -0.1700

Data Index: 1265094 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 3.1271. Min Range: -3.1271

Max Act: 3.0798. Min Act: -0.1700

Data Index: 908858 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 3.1271. Min Range: -3.1271

Max Act: 3.0798. Min Act: -0.1700

Data Index: 14475 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 3.1271. Min Range: -3.1271

Max Act: 3.0798. Min Act: -0.1700

Data Index: 131026 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 3.1271. Min Range: -3.1271

Max Act: 3.0955. Min Act: -0.1700

Data Index: 918881 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 3.1271. Min Range: -3.1271

Max Act: 3.0798. Min Act: -0.1700

Data Index: 923885 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 3.1271. Min Range: -3.1271

Max Act: 3.1271. Min Act: -0.1700

Data Index: 439680 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 3.1271. Min Range: -3.1271

Max Act: 3.0798. Min Act: -0.1700

Data Index: 107886 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 3.1271. Min Range: -3.1271

Max Act: 3.0798. Min Act: -0.1700

Data Index: 368704 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 3.1271. Min Range: -3.1271

Max Act: 3.0798. Min Act: -0.1700

Data Index: 365887 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 3.1271. Min Range: -3.1271

Max Act: 3.0640. Min Act: -0.1700

Data Index: 776904 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 3.1271. Min Range: -3.1271

Max Act: 3.0798. Min Act: -0.1700

Data Index: 1038317 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 3.1271. Min Range: -3.1271

Max Act: 3.0798. Min Act: -0.1700

Data Index: 826250 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 3.1271. Min Range: -3.1271

Max Act: 3.0798. Min Act: -0.1700

Data Index: 306676 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 3.1271. Min Range: -3.1271

Max Act: 3.0640. Min Act: -0.1700

Data Index: 570961 (C4 (Web Text))

Max Activating Token Index: 358