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

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

Neuron 1509 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: 3.5504. Min Range: -3.5504

Max Act: 3.5504. Min Act: -0.1700

Data Index: 182059 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 3.5504. Min Range: -3.5504

Max Act: 3.5191. Min Act: -0.1700

Data Index: 339233 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 3.5504. Min Range: -3.5504

Max Act: 3.4250. Min Act: -0.1700

Data Index: 1339915 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 3.5504. Min Range: -3.5504

Max Act: 3.4250. Min Act: -0.1700

Data Index: 990444 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 3.5504. Min Range: -3.5504

Max Act: 3.3309. Min Act: -0.1700

Data Index: 924861 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 3.5504. Min Range: -3.5504

Max Act: 3.3309. Min Act: -0.1700

Data Index: 1188312 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 3.5504. Min Range: -3.5504

Max Act: 3.3623. Min Act: -0.1700

Data Index: 429297 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 3.5504. Min Range: -3.5504

Max Act: 3.4564. Min Act: -0.1700

Data Index: 1307641 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 3.5504. Min Range: -3.5504

Max Act: 3.2367. Min Act: -0.1700

Data Index: 779340 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 3.5504. Min Range: -3.5504

Max Act: 3.3309. Min Act: -0.1700

Data Index: 519863 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 3.5504. Min Range: -3.5504

Max Act: 3.2367. Min Act: -0.1700

Data Index: 201470 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 3.5504. Min Range: -3.5504

Max Act: 3.2681. Min Act: -0.1700

Data Index: 493404 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 3.5504. Min Range: -3.5504

Max Act: 3.3309. Min Act: -0.1700

Data Index: 1089013 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 3.5504. Min Range: -3.5504

Max Act: 3.2681. Min Act: -0.1700

Data Index: 1147657 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 3.5504. Min Range: -3.5504

Max Act: 3.2367. Min Act: -0.1700

Data Index: 75424 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 3.5504. Min Range: -3.5504

Max Act: 3.1737. Min Act: -0.1700

Data Index: 1134313 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 3.5504. Min Range: -3.5504

Max Act: 3.2367. Min Act: -0.1700

Data Index: 848166 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 3.5504. Min Range: -3.5504

Max Act: 3.2367. Min Act: -0.1700

Data Index: 327650 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 3.5504. Min Range: -3.5504

Max Act: 3.2052. Min Act: -0.1700

Data Index: 898074 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 3.5504. Min Range: -3.5504

Max Act: 3.2367. Min Act: -0.1700

Data Index: 912619 (C4 (Web Text))

Max Activating Token Index: 634