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

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

Neuron 1812 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: 3.1714. Min Range: -3.1714

Max Act: 3.1714. Min Act: -0.1700

Data Index: 1031199 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.1714. Min Range: -3.1714

Max Act: 3.1557. Min Act: -0.1700

Data Index: 737832 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 3.1714. Min Range: -3.1714

Max Act: 3.1242. Min Act: -0.1700

Data Index: 1532694 (Python Code)

Max Activating Token Index: 802

Text #3

Max Range: 3.1714. Min Range: -3.1714

Max Act: 3.1084. Min Act: -0.1700

Data Index: 1246856 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 3.1714. Min Range: -3.1714

Max Act: 3.0769. Min Act: -0.1700

Data Index: 960489 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 3.1714. Min Range: -3.1714

Max Act: 3.0927. Min Act: -0.1700

Data Index: 82110 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 3.1714. Min Range: -3.1714

Max Act: 3.1084. Min Act: -0.1700

Data Index: 1254502 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 3.1714. Min Range: -3.1714

Max Act: 3.0611. Min Act: -0.1700

Data Index: 1569469 (Python Code)

Max Activating Token Index: 943

Text #8

Max Range: 3.1714. Min Range: -3.1714

Max Act: 3.0769. Min Act: -0.1700

Data Index: 1487133 (Python Code)

Max Activating Token Index: 17

Text #9

Max Range: 3.1714. Min Range: -3.1714

Max Act: 3.0769. Min Act: -0.1700

Data Index: 1387393 (Python Code)

Max Activating Token Index: 19

Text #10

Max Range: 3.1714. Min Range: -3.1714

Max Act: 3.1084. Min Act: -0.1700

Data Index: 1307846 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 3.1714. Min Range: -3.1714

Max Act: 3.0453. Min Act: -0.1700

Data Index: 837280 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 3.1714. Min Range: -3.1714

Max Act: 3.0769. Min Act: -0.1700

Data Index: 586467 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 3.1714. Min Range: -3.1714

Max Act: 3.0295. Min Act: -0.1700

Data Index: 893895 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 3.1714. Min Range: -3.1714

Max Act: 3.0295. Min Act: -0.1700

Data Index: 1170523 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 3.1714. Min Range: -3.1714

Max Act: 3.0453. Min Act: -0.1700

Data Index: 311204 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 3.1714. Min Range: -3.1714

Max Act: 3.0453. Min Act: -0.1700

Data Index: 737083 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 3.1714. Min Range: -3.1714

Max Act: 3.0137. Min Act: -0.1700

Data Index: 1035083 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 3.1714. Min Range: -3.1714

Max Act: 3.0295. Min Act: -0.1700

Data Index: 36508 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 3.1714. Min Range: -3.1714

Max Act: 3.0295. Min Act: -0.1700

Data Index: 814496 (C4 (Web Text))

Max Activating Token Index: 925