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

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

Neuron 368 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.1359. Min Range: -5.1359

Max Act: 5.1359. Min Act: -0.1700

Data Index: 74646 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 5.1359. Min Range: -5.1359

Max Act: 5.0421. Min Act: -0.1700

Data Index: 1555164 (Python Code)

Max Activating Token Index: 626

Text #2

Max Range: 5.1359. Min Range: -5.1359

Max Act: 4.9484. Min Act: -0.1700

Data Index: 670480 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 5.1359. Min Range: -5.1359

Max Act: 4.8234. Min Act: -0.1700

Data Index: 1502686 (Python Code)

Max Activating Token Index: 486

Text #4

Max Range: 5.1359. Min Range: -5.1359

Max Act: 4.9171. Min Act: -0.1700

Data Index: 312454 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 5.1359. Min Range: -5.1359

Max Act: 4.9171. Min Act: -0.1700

Data Index: 518056 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 5.1359. Min Range: -5.1359

Max Act: 4.9171. Min Act: -0.1700

Data Index: 583312 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 5.1359. Min Range: -5.1359

Max Act: 4.9171. Min Act: -0.1700

Data Index: 126865 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 5.1359. Min Range: -5.1359

Max Act: 4.8859. Min Act: -0.1700

Data Index: 486121 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 5.1359. Min Range: -5.1359

Max Act: 4.8546. Min Act: -0.1700

Data Index: 956221 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 5.1359. Min Range: -5.1359

Max Act: 4.8546. Min Act: -0.1700

Data Index: 912787 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 5.1359. Min Range: -5.1359

Max Act: 4.8546. Min Act: -0.1700

Data Index: 1275064 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 5.1359. Min Range: -5.1359

Max Act: 4.8859. Min Act: -0.1700

Data Index: 1128169 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 5.1359. Min Range: -5.1359

Max Act: 4.8546. Min Act: -0.1700

Data Index: 175181 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 5.1359. Min Range: -5.1359

Max Act: 4.8859. Min Act: -0.1700

Data Index: 239248 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 5.1359. Min Range: -5.1359

Max Act: 4.7921. Min Act: -0.1700

Data Index: 153733 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 5.1359. Min Range: -5.1359

Max Act: 4.8234. Min Act: -0.1700

Data Index: 106850 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 5.1359. Min Range: -5.1359

Max Act: 4.7921. Min Act: -0.1700

Data Index: 1074535 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 5.1359. Min Range: -5.1359

Max Act: 4.8546. Min Act: -0.1700

Data Index: 153722 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 5.1359. Min Range: -5.1359

Max Act: 4.7921. Min Act: -0.1700

Data Index: 564729 (C4 (Web Text))

Max Activating Token Index: 1014