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

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

Neuron 1297 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: 3.9139. Min Range: -3.9139

Max Act: 3.9139. Min Act: -0.1700

Data Index: 837225 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.8357. Min Act: -0.1699

Data Index: 832759 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.8357. Min Act: -0.1700

Data Index: 1445978 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.8357. Min Act: -0.1700

Data Index: 1472116 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.8357. Min Act: -0.1700

Data Index: 1440344 (Python Code)

Max Activating Token Index: 3

Text #5

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.8357. Min Act: -0.1700

Data Index: 1455370 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.8514. Min Act: -0.1700

Data Index: 1498737 (Python Code)

Max Activating Token Index: 17

Text #7

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.8357. Min Act: -0.1700

Data Index: 1629529 (Python Code)

Max Activating Token Index: 3

Text #8

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.8357. Min Act: -0.1700

Data Index: 1448033 (Python Code)

Max Activating Token Index: 3

Text #9

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.8357. Min Act: -0.1700

Data Index: 116425 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.8357. Min Act: -0.1700

Data Index: 1211868 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.8045. Min Act: -0.1700

Data Index: 1147146 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.8201. Min Act: -0.1700

Data Index: 596905 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.8045. Min Act: -0.1700

Data Index: 1295505 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.7575. Min Act: -0.1700

Data Index: 578912 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.7732. Min Act: -0.1700

Data Index: 1026916 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.7419. Min Act: -0.1700

Data Index: 176866 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.7575. Min Act: -0.1700

Data Index: 762815 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.7262. Min Act: -0.1700

Data Index: 1335861 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.7262. Min Act: -0.1700

Data Index: 29673 (C4 (Web Text))

Max Activating Token Index: 872