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

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

Neuron 1331 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.4822. Min Act: -0.1700

Data Index: 973552 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.4510. Min Act: -0.1700

Data Index: 660277 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.3885. Min Act: -0.1700

Data Index: 455067 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.3885. Min Act: -0.1700

Data Index: 788331 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.3260. Min Act: -0.1700

Data Index: 919839 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.2635. Min Act: -0.1700

Data Index: 802127 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.2947. Min Act: -0.1700

Data Index: 676870 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.2947. Min Act: -0.1700

Data Index: 717376 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.2947. Min Act: -0.1700

Data Index: 311882 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.2010. Min Act: -0.1700

Data Index: 819738 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.2010. Min Act: -0.1700

Data Index: 615680 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.1697. Min Act: -0.1700

Data Index: 547355 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.2010. Min Act: -0.1700

Data Index: 836228 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.1385. Min Act: -0.1700

Data Index: 677331 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.1385. Min Act: -0.1700

Data Index: 314841 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.1697. Min Act: -0.1699

Data Index: 651298 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.1385. Min Act: -0.1700

Data Index: 1185191 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.1385. Min Act: -0.1700

Data Index: 744526 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.1385. Min Act: -0.1700

Data Index: 648836 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 5.4822. Min Range: -5.4822

Max Act: 5.1385. Min Act: -0.1700

Data Index: 970617 (C4 (Web Text))

Max Activating Token Index: 941