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

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

Neuron 1967 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: 3.2805. Min Range: -3.2805

Max Act: 3.2805. Min Act: -0.1700

Data Index: 310313 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 3.2805. Min Range: -3.2805

Max Act: 3.2647. Min Act: -0.1700

Data Index: 865969 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 3.2805. Min Range: -3.2805

Max Act: 3.2176. Min Act: -0.1700

Data Index: 865183 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 3.2805. Min Range: -3.2805

Max Act: 3.2019. Min Act: -0.1700

Data Index: 332105 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 3.2805. Min Range: -3.2805

Max Act: 3.1861. Min Act: -0.1700

Data Index: 1055639 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 3.2805. Min Range: -3.2805

Max Act: 3.2019. Min Act: -0.1700

Data Index: 773386 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 3.2805. Min Range: -3.2805

Max Act: 3.1389. Min Act: -0.1700

Data Index: 378951 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 3.2805. Min Range: -3.2805

Max Act: 3.1389. Min Act: -0.1700

Data Index: 512042 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 3.2805. Min Range: -3.2805

Max Act: 3.1389. Min Act: -0.1700

Data Index: 1358872 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 3.2805. Min Range: -3.2805

Max Act: 3.1389. Min Act: -0.1700

Data Index: 962556 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 3.2805. Min Range: -3.2805

Max Act: 3.1546. Min Act: -0.1700

Data Index: 1115079 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 3.2805. Min Range: -3.2805

Max Act: 3.1546. Min Act: -0.1700

Data Index: 72505 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 3.2805. Min Range: -3.2805

Max Act: 3.1704. Min Act: -0.1700

Data Index: 1237632 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 3.2805. Min Range: -3.2805

Max Act: 3.1546. Min Act: -0.1700

Data Index: 979729 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 3.2805. Min Range: -3.2805

Max Act: 3.1389. Min Act: -0.1700

Data Index: 19573 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 3.2805. Min Range: -3.2805

Max Act: 3.1231. Min Act: -0.1700

Data Index: 1039009 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 3.2805. Min Range: -3.2805

Max Act: 3.1389. Min Act: -0.1700

Data Index: 1044119 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 3.2805. Min Range: -3.2805

Max Act: 3.1389. Min Act: -0.1700

Data Index: 548258 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 3.2805. Min Range: -3.2805

Max Act: 3.1231. Min Act: -0.1700

Data Index: 73881 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 3.2805. Min Range: -3.2805

Max Act: 3.1546. Min Act: -0.1700

Data Index: 309951 (C4 (Web Text))

Max Activating Token Index: 345