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

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

Neuron 1738 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: 3.2770. Min Range: -3.2770

Max Act: 3.2770. Min Act: -0.1700

Data Index: 1092464 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1669. Min Act: -0.1700

Data Index: 452373 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1827. Min Act: -0.1700

Data Index: 1616193 (Python Code)

Max Activating Token Index: 1011

Text #3

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1669. Min Act: -0.1700

Data Index: 116256 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1827. Min Act: -0.1700

Data Index: 1614816 (Python Code)

Max Activating Token Index: 7

Text #5

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1039. Min Act: -0.1700

Data Index: 427266 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1669. Min Act: -0.1700

Data Index: 1547820 (Python Code)

Max Activating Token Index: 845

Text #7

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1512. Min Act: -0.1700

Data Index: 1625638 (Python Code)

Max Activating Token Index: 385

Text #8

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1512. Min Act: -0.1700

Data Index: 493488 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1354. Min Act: -0.1700

Data Index: 1507699 (Python Code)

Max Activating Token Index: 452

Text #10

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1197. Min Act: -0.1700

Data Index: 1218061 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1197. Min Act: -0.1700

Data Index: 987368 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1039. Min Act: -0.1700

Data Index: 627231 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1197. Min Act: -0.1700

Data Index: 1049613 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.0724. Min Act: -0.1700

Data Index: 462630 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1039. Min Act: -0.1700

Data Index: 1484196 (Python Code)

Max Activating Token Index: 319

Text #16

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1039. Min Act: -0.1700

Data Index: 1538027 (Python Code)

Max Activating Token Index: 772

Text #17

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.0881. Min Act: -0.1700

Data Index: 645215 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1039. Min Act: -0.1700

Data Index: 829220 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1354. Min Act: -0.1700

Data Index: 589522 (C4 (Web Text))

Max Activating Token Index: 561