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

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

Neuron 1463 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: 3.5503. Min Range: -3.5503

Max Act: 3.5503. Min Act: -0.1700

Data Index: 1015653 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.4876. Min Act: -0.1700

Data Index: 82301 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.4249. Min Act: -0.1700

Data Index: 133891 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.3621. Min Act: -0.1700

Data Index: 285242 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.3308. Min Act: -0.1700

Data Index: 1358771 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.3621. Min Act: -0.1700

Data Index: 1096525 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.3151. Min Act: -0.1700

Data Index: 297131 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.2993. Min Act: -0.1700

Data Index: 1502846 (Python Code)

Max Activating Token Index: 555

Text #8

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.2993. Min Act: -0.1700

Data Index: 143155 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.2993. Min Act: -0.1700

Data Index: 461 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.2365. Min Act: -0.1700

Data Index: 1233391 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.2679. Min Act: -0.1700

Data Index: 581608 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.2679. Min Act: -0.1700

Data Index: 1105531 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.2522. Min Act: -0.1700

Data Index: 97793 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.2522. Min Act: -0.1700

Data Index: 1449661 (Python Code)

Max Activating Token Index: 833

Text #15

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.2679. Min Act: -0.1700

Data Index: 1637028 (Python Code)

Max Activating Token Index: 39

Text #16

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.2836. Min Act: -0.1700

Data Index: 1593260 (Python Code)

Max Activating Token Index: 35

Text #17

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.2522. Min Act: -0.1700

Data Index: 1409148 (Python Code)

Max Activating Token Index: 567

Text #18

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.2679. Min Act: -0.1700

Data Index: 1383555 (Python Code)

Max Activating Token Index: 494

Text #19

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.2365. Min Act: -0.1700

Data Index: 1431305 (Python Code)

Max Activating Token Index: 823