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

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

Neuron 218 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: 7.9936. Min Range: -7.9936

Max Act: 7.9936. Min Act: -0.1700

Data Index: 197158 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 7.9936. Min Range: -7.9936

Max Act: 7.8999. Min Act: -0.1700

Data Index: 192615 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 7.9936. Min Range: -7.9936

Max Act: 7.7749. Min Act: -0.1700

Data Index: 1088992 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 7.9936. Min Range: -7.9936

Max Act: 7.7124. Min Act: -0.1700

Data Index: 328782 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 7.9936. Min Range: -7.9936

Max Act: 7.6811. Min Act: -0.1700

Data Index: 734893 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 7.9936. Min Range: -7.9936

Max Act: 7.5874. Min Act: -0.1699

Data Index: 1215645 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 7.9936. Min Range: -7.9936

Max Act: 7.5561. Min Act: -0.1700

Data Index: 968251 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 7.9936. Min Range: -7.9936

Max Act: 7.4936. Min Act: -0.1700

Data Index: 861082 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 7.9936. Min Range: -7.9936

Max Act: 7.5561. Min Act: -0.1700

Data Index: 160999 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 7.9936. Min Range: -7.9936

Max Act: 7.4624. Min Act: -0.1700

Data Index: 950035 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 7.9936. Min Range: -7.9936

Max Act: 7.4624. Min Act: -0.1700

Data Index: 469542 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 7.9936. Min Range: -7.9936

Max Act: 7.3999. Min Act: -0.1700

Data Index: 84846 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 7.9936. Min Range: -7.9936

Max Act: 7.3686. Min Act: -0.1700

Data Index: 328022 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 7.9936. Min Range: -7.9936

Max Act: 7.3686. Min Act: -0.1700

Data Index: 108237 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 7.9936. Min Range: -7.9936

Max Act: 7.3999. Min Act: -0.1700

Data Index: 11448 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 7.9936. Min Range: -7.9936

Max Act: 7.3686. Min Act: -0.1700

Data Index: 812775 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 7.9936. Min Range: -7.9936

Max Act: 7.3686. Min Act: -0.1700

Data Index: 827587 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 7.9936. Min Range: -7.9936

Max Act: 7.3061. Min Act: -0.1700

Data Index: 874421 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 7.9936. Min Range: -7.9936

Max Act: 7.3061. Min Act: -0.1700

Data Index: 142030 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 7.9936. Min Range: -7.9936

Max Act: 7.3061. Min Act: -0.1700

Data Index: 270127 (C4 (Web Text))

Max Activating Token Index: 801