Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1370 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.5751. Min Range: -5.5751

Max Act: 5.5751. Min Act: -0.1700

Data Index: 429126 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 5.5751. Min Range: -5.5751

Max Act: 5.5751. Min Act: -0.1700

Data Index: 717915 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 5.5751. Min Range: -5.5751

Max Act: 5.5439. Min Act: -0.1700

Data Index: 772880 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 5.5751. Min Range: -5.5751

Max Act: 5.5439. Min Act: -0.1700

Data Index: 486803 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 5.5751. Min Range: -5.5751

Max Act: 5.4501. Min Act: -0.1700

Data Index: 760345 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 5.5751. Min Range: -5.5751

Max Act: 5.4189. Min Act: -0.1700

Data Index: 675561 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 5.5751. Min Range: -5.5751

Max Act: 5.3564. Min Act: -0.1700

Data Index: 512545 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 5.5751. Min Range: -5.5751

Max Act: 5.3876. Min Act: -0.1700

Data Index: 181766 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 5.5751. Min Range: -5.5751

Max Act: 5.3876. Min Act: -0.1700

Data Index: 1244054 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 5.5751. Min Range: -5.5751

Max Act: 5.3564. Min Act: -0.1700

Data Index: 1310501 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 5.5751. Min Range: -5.5751

Max Act: 5.3876. Min Act: -0.1700

Data Index: 17687 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 5.5751. Min Range: -5.5751

Max Act: 5.3251. Min Act: -0.1700

Data Index: 990226 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 5.5751. Min Range: -5.5751

Max Act: 5.2939. Min Act: -0.1700

Data Index: 933423 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 5.5751. Min Range: -5.5751

Max Act: 5.2626. Min Act: -0.1700

Data Index: 127889 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 5.5751. Min Range: -5.5751

Max Act: 5.2626. Min Act: -0.1700

Data Index: 133241 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 5.5751. Min Range: -5.5751

Max Act: 5.2939. Min Act: -0.1700

Data Index: 347287 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 5.5751. Min Range: -5.5751

Max Act: 5.2626. Min Act: -0.1700

Data Index: 742317 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 5.5751. Min Range: -5.5751

Max Act: 5.2626. Min Act: -0.1700

Data Index: 708858 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 5.5751. Min Range: -5.5751

Max Act: 5.2626. Min Act: -0.1700

Data Index: 155008 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 5.5751. Min Range: -5.5751

Max Act: 5.2626. Min Act: -0.1700

Data Index: 834368 (C4 (Web Text))

Max Activating Token Index: 525