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

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

Neuron 222 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6289. Min Range: -3.6289

Max Act: 3.5663. Min Act: -0.1700

Data Index: 1322197 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 3.6289. Min Range: -3.6289

Max Act: 3.5663. Min Act: -0.1700

Data Index: 699994 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 3.6289. Min Range: -3.6289

Max Act: 3.6289. Min Act: -0.1700

Data Index: 981829 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 3.6289. Min Range: -3.6289

Max Act: 3.5976. Min Act: -0.1700

Data Index: 77192 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 3.6289. Min Range: -3.6289

Max Act: 3.5976. Min Act: -0.1700

Data Index: 180398 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 3.6289. Min Range: -3.6289

Max Act: 3.5350. Min Act: -0.1700

Data Index: 730077 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 3.6289. Min Range: -3.6289

Max Act: 3.5037. Min Act: -0.1700

Data Index: 771780 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 3.6289. Min Range: -3.6289

Max Act: 3.5350. Min Act: -0.1700

Data Index: 1019959 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 3.6289. Min Range: -3.6289

Max Act: 3.5037. Min Act: -0.1700

Data Index: 902475 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 3.6289. Min Range: -3.6289

Max Act: 3.5037. Min Act: -0.1700

Data Index: 1019090 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 3.6289. Min Range: -3.6289

Max Act: 3.4723. Min Act: -0.1700

Data Index: 897625 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 3.6289. Min Range: -3.6289

Max Act: 3.4723. Min Act: -0.1700

Data Index: 1118047 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 3.6289. Min Range: -3.6289

Max Act: 3.4723. Min Act: -0.1700

Data Index: 875904 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 3.6289. Min Range: -3.6289

Max Act: 3.4410. Min Act: -0.1700

Data Index: 175375 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 3.6289. Min Range: -3.6289

Max Act: 3.4723. Min Act: -0.1700

Data Index: 959744 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 3.6289. Min Range: -3.6289

Max Act: 3.4096. Min Act: -0.1700

Data Index: 119175 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 3.6289. Min Range: -3.6289

Max Act: 3.4096. Min Act: -0.1700

Data Index: 1176181 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 3.6289. Min Range: -3.6289

Max Act: 3.4096. Min Act: -0.1700

Data Index: 903366 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 3.6289. Min Range: -3.6289

Max Act: 3.4723. Min Act: -0.1700

Data Index: 871382 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 3.6289. Min Range: -3.6289

Max Act: 3.3469. Min Act: -0.1700

Data Index: 607368 (C4 (Web Text))

Max Activating Token Index: 815