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

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

Neuron 539 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: 5.9203. Min Range: -5.9203

Max Act: 5.9203. Min Act: -0.1700

Data Index: 111863 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.5453. Min Act: -0.1700

Data Index: 427605 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.5766. Min Act: -0.1700

Data Index: 853454 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.4516. Min Act: -0.1700

Data Index: 776938 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.3578. Min Act: -0.1700

Data Index: 269743 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.3578. Min Act: -0.1700

Data Index: 801071 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.4203. Min Act: -0.1700

Data Index: 797186 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.4516. Min Act: -0.1700

Data Index: 1258813 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.5141. Min Act: -0.1700

Data Index: 1001245 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.3891. Min Act: -0.1700

Data Index: 1324479 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.4203. Min Act: -0.1700

Data Index: 1054716 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.3266. Min Act: -0.1700

Data Index: 1292742 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.3578. Min Act: -0.1700

Data Index: 157483 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.3891. Min Act: -0.1700

Data Index: 1165857 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.3578. Min Act: -0.1700

Data Index: 113732 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.3891. Min Act: -0.1700

Data Index: 1082435 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.3266. Min Act: -0.1700

Data Index: 133761 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.2953. Min Act: -0.1700

Data Index: 937583 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.2953. Min Act: -0.1700

Data Index: 160265 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.3266. Min Act: -0.1700

Data Index: 857309 (C4 (Web Text))

Max Activating Token Index: 626