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

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

Neuron 810 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6823. Min Range: -3.6823

Max Act: 3.6823. Min Act: -0.1700

Data Index: 99917 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 3.6823. Min Range: -3.6823

Max Act: 3.5570. Min Act: -0.1700

Data Index: 588866 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 3.6823. Min Range: -3.6823

Max Act: 3.5570. Min Act: -0.1700

Data Index: 867962 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 3.6823. Min Range: -3.6823

Max Act: 3.5727. Min Act: -0.1700

Data Index: 402018 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 3.6823. Min Range: -3.6823

Max Act: 3.5727. Min Act: -0.1700

Data Index: 531894 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 3.6823. Min Range: -3.6823

Max Act: 3.5570. Min Act: -0.1700

Data Index: 676864 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 3.6823. Min Range: -3.6823

Max Act: 3.5257. Min Act: -0.1700

Data Index: 1017116 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 3.6823. Min Range: -3.6823

Max Act: 3.4944. Min Act: -0.1700

Data Index: 1311335 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 3.6823. Min Range: -3.6823

Max Act: 3.5100. Min Act: -0.1700

Data Index: 1131579 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 3.6823. Min Range: -3.6823

Max Act: 3.5257. Min Act: -0.1700

Data Index: 1315223 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 3.6823. Min Range: -3.6823

Max Act: 3.4474. Min Act: -0.1700

Data Index: 26214 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 3.6823. Min Range: -3.6823

Max Act: 3.4474. Min Act: -0.1700

Data Index: 1060047 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 3.6823. Min Range: -3.6823

Max Act: 3.4317. Min Act: -0.1700

Data Index: 53493 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 3.6823. Min Range: -3.6823

Max Act: 3.4160. Min Act: -0.1700

Data Index: 189010 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 3.6823. Min Range: -3.6823

Max Act: 3.4317. Min Act: -0.1700

Data Index: 496512 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 3.6823. Min Range: -3.6823

Max Act: 3.3846. Min Act: -0.1700

Data Index: 1171162 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 3.6823. Min Range: -3.6823

Max Act: 3.3846. Min Act: -0.1700

Data Index: 698527 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 3.6823. Min Range: -3.6823

Max Act: 3.4160. Min Act: -0.1700

Data Index: 82278 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 3.6823. Min Range: -3.6823

Max Act: 3.4474. Min Act: -0.1700

Data Index: 165780 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 3.6823. Min Range: -3.6823

Max Act: 3.3846. Min Act: -0.1700

Data Index: 837162 (C4 (Web Text))

Max Activating Token Index: 834