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

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

Neuron 445 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6864. Min Range: -3.6864

Max Act: 3.6864. Min Act: -0.1700

Data Index: 122488 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 3.6864. Min Range: -3.6864

Max Act: 3.6238. Min Act: -0.1700

Data Index: 577882 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 3.6864. Min Range: -3.6864

Max Act: 3.6081. Min Act: -0.1700

Data Index: 632157 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 3.6864. Min Range: -3.6864

Max Act: 3.5768. Min Act: -0.1700

Data Index: 915636 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 3.6864. Min Range: -3.6864

Max Act: 3.5141. Min Act: -0.1700

Data Index: 659154 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 3.6864. Min Range: -3.6864

Max Act: 3.5611. Min Act: -0.1700

Data Index: 1265597 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 3.6864. Min Range: -3.6864

Max Act: 3.5298. Min Act: -0.1700

Data Index: 775794 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 3.6864. Min Range: -3.6864

Max Act: 3.4358. Min Act: -0.1700

Data Index: 982303 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 3.6864. Min Range: -3.6864

Max Act: 3.4671. Min Act: -0.1700

Data Index: 1076561 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 3.6864. Min Range: -3.6864

Max Act: 3.4515. Min Act: -0.1700

Data Index: 938366 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 3.6864. Min Range: -3.6864

Max Act: 3.4985. Min Act: -0.1700

Data Index: 271178 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 3.6864. Min Range: -3.6864

Max Act: 3.4985. Min Act: -0.1700

Data Index: 463266 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 3.6864. Min Range: -3.6864

Max Act: 3.4828. Min Act: -0.1700

Data Index: 863085 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 3.6864. Min Range: -3.6864

Max Act: 3.4515. Min Act: -0.1700

Data Index: 775976 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 3.6864. Min Range: -3.6864

Max Act: 3.4515. Min Act: -0.1700

Data Index: 1064456 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 3.6864. Min Range: -3.6864

Max Act: 3.4201. Min Act: -0.1700

Data Index: 1091891 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 3.6864. Min Range: -3.6864

Max Act: 3.4201. Min Act: -0.1700

Data Index: 250386 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 3.6864. Min Range: -3.6864

Max Act: 3.4044. Min Act: -0.1700

Data Index: 406748 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 3.6864. Min Range: -3.6864

Max Act: 3.4044. Min Act: -0.1700

Data Index: 943919 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 3.6864. Min Range: -3.6864

Max Act: 3.4358. Min Act: -0.1700

Data Index: 663141 (C4 (Web Text))

Max Activating Token Index: 743