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

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

Neuron 1217 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: 5.7436. Min Range: -5.7436

Max Act: 5.7436. Min Act: -0.1700

Data Index: 381353 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 5.7436. Min Range: -5.7436

Max Act: 5.7124. Min Act: -0.1700

Data Index: 10125 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 5.7436. Min Range: -5.7436

Max Act: 5.6811. Min Act: -0.1700

Data Index: 672359 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 5.7436. Min Range: -5.7436

Max Act: 5.6811. Min Act: -0.1700

Data Index: 536870 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 5.7436. Min Range: -5.7436

Max Act: 5.6186. Min Act: -0.1700

Data Index: 909091 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 5.7436. Min Range: -5.7436

Max Act: 5.5874. Min Act: -0.1700

Data Index: 263801 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 5.7436. Min Range: -5.7436

Max Act: 5.5561. Min Act: -0.1700

Data Index: 810045 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 5.7436. Min Range: -5.7436

Max Act: 5.5249. Min Act: -0.1700

Data Index: 652856 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 5.7436. Min Range: -5.7436

Max Act: 5.4936. Min Act: -0.1700

Data Index: 236855 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 5.7436. Min Range: -5.7436

Max Act: 5.4936. Min Act: -0.1700

Data Index: 775705 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 5.7436. Min Range: -5.7436

Max Act: 5.4624. Min Act: -0.1700

Data Index: 10866 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 5.7436. Min Range: -5.7436

Max Act: 5.4624. Min Act: -0.1700

Data Index: 995936 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 5.7436. Min Range: -5.7436

Max Act: 5.4936. Min Act: -0.1700

Data Index: 663107 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 5.7436. Min Range: -5.7436

Max Act: 5.4936. Min Act: -0.1700

Data Index: 750496 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 5.7436. Min Range: -5.7436

Max Act: 5.3686. Min Act: -0.1700

Data Index: 36774 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 5.7436. Min Range: -5.7436

Max Act: 5.4311. Min Act: -0.1700

Data Index: 704518 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 5.7436. Min Range: -5.7436

Max Act: 5.4311. Min Act: -0.1700

Data Index: 302682 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 5.7436. Min Range: -5.7436

Max Act: 5.3999. Min Act: -0.1700

Data Index: 746310 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 5.7436. Min Range: -5.7436

Max Act: 5.3999. Min Act: -0.1700

Data Index: 437098 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 5.7436. Min Range: -5.7436

Max Act: 5.3999. Min Act: -0.1700

Data Index: 1348416 (C4 (Web Text))

Max Activating Token Index: 97