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

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

Neuron 476 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: 3.3285. Min Range: -3.3285

Max Act: 3.2814. Min Act: -0.1700

Data Index: 714902 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.2028. Min Act: -0.1700

Data Index: 496083 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.3285. Min Act: -0.1700

Data Index: 323754 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1713. Min Act: -0.1700

Data Index: 1137809 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1713. Min Act: -0.1700

Data Index: 977723 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1241. Min Act: -0.1700

Data Index: 895445 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.0926. Min Act: -0.1700

Data Index: 187446 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.0610. Min Act: -0.1700

Data Index: 453515 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1241. Min Act: -0.1700

Data Index: 636718 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.0294. Min Act: -0.1700

Data Index: 1310322 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.0768. Min Act: -0.1700

Data Index: 586166 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.0768. Min Act: -0.1700

Data Index: 35819 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.0768. Min Act: -0.1700

Data Index: 259221 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1241. Min Act: -0.1700

Data Index: 483695 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.0294. Min Act: -0.1700

Data Index: 90002 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 3.3285. Min Range: -3.3285

Max Act: 2.9662. Min Act: -0.1700

Data Index: 135328 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.0294. Min Act: -0.1700

Data Index: 584106 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.0136. Min Act: -0.1700

Data Index: 554092 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.0294. Min Act: -0.1700

Data Index: 463998 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 3.3285. Min Range: -3.3285

Max Act: 2.9978. Min Act: -0.1700

Data Index: 619708 (C4 (Web Text))

Max Activating Token Index: 471