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

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

Neuron 1818 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.4235. Min Range: -5.4235

Max Act: 5.4235. Min Act: -0.1700

Data Index: 24531 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 5.4235. Min Range: -5.4235

Max Act: 5.3610. Min Act: -0.1700

Data Index: 1101791 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 5.4235. Min Range: -5.4235

Max Act: 5.3922. Min Act: -0.1700

Data Index: 232326 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 5.4235. Min Range: -5.4235

Max Act: 5.3610. Min Act: -0.1700

Data Index: 827464 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 5.4235. Min Range: -5.4235

Max Act: 5.3610. Min Act: -0.1700

Data Index: 573768 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 5.4235. Min Range: -5.4235

Max Act: 5.3297. Min Act: -0.1700

Data Index: 1011568 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 5.4235. Min Range: -5.4235

Max Act: 5.3610. Min Act: -0.1700

Data Index: 873120 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 5.4235. Min Range: -5.4235

Max Act: 5.2672. Min Act: -0.1700

Data Index: 391557 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 5.4235. Min Range: -5.4235

Max Act: 5.2672. Min Act: -0.1700

Data Index: 860498 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 5.4235. Min Range: -5.4235

Max Act: 5.2672. Min Act: -0.1700

Data Index: 677165 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 5.4235. Min Range: -5.4235

Max Act: 5.2360. Min Act: -0.1700

Data Index: 8920 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 5.4235. Min Range: -5.4235

Max Act: 5.1735. Min Act: -0.1700

Data Index: 954852 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 5.4235. Min Range: -5.4235

Max Act: 5.2047. Min Act: -0.1700

Data Index: 656014 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 5.4235. Min Range: -5.4235

Max Act: 5.1735. Min Act: -0.1700

Data Index: 1086234 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 5.4235. Min Range: -5.4235

Max Act: 5.1422. Min Act: -0.1700

Data Index: 219951 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 5.4235. Min Range: -5.4235

Max Act: 5.1110. Min Act: -0.1700

Data Index: 673157 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 5.4235. Min Range: -5.4235

Max Act: 5.1735. Min Act: -0.1700

Data Index: 91896 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 5.4235. Min Range: -5.4235

Max Act: 5.1422. Min Act: -0.1700

Data Index: 430011 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 5.4235. Min Range: -5.4235

Max Act: 5.1110. Min Act: -0.1700

Data Index: 564963 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 5.4235. Min Range: -5.4235

Max Act: 5.1422. Min Act: -0.1700

Data Index: 676603 (C4 (Web Text))

Max Activating Token Index: 509