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

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

Neuron 1928 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: 3.9514. Min Range: -3.9514

Max Act: 3.9201. Min Act: -0.1700

Data Index: 1525936 (Python Code)

Max Activating Token Index: 907

Text #1

Max Range: 3.9514. Min Range: -3.9514

Max Act: 3.9514. Min Act: -0.1700

Data Index: 1621234 (Python Code)

Max Activating Token Index: 854

Text #2

Max Range: 3.9514. Min Range: -3.9514

Max Act: 3.8888. Min Act: -0.1700

Data Index: 1495684 (Python Code)

Max Activating Token Index: 692

Text #3

Max Range: 3.9514. Min Range: -3.9514

Max Act: 3.8888. Min Act: -0.1700

Data Index: 1389791 (Python Code)

Max Activating Token Index: 956

Text #4

Max Range: 3.9514. Min Range: -3.9514

Max Act: 3.8263. Min Act: -0.1700

Data Index: 1465257 (Python Code)

Max Activating Token Index: 324

Text #5

Max Range: 3.9514. Min Range: -3.9514

Max Act: 3.8263. Min Act: -0.1700

Data Index: 1649089 (Python Code)

Max Activating Token Index: 1022

Text #6

Max Range: 3.9514. Min Range: -3.9514

Max Act: 3.8576. Min Act: -0.1700

Data Index: 1503728 (Python Code)

Max Activating Token Index: 840

Text #7

Max Range: 3.9514. Min Range: -3.9514

Max Act: 3.8576. Min Act: -0.1700

Data Index: 1530783 (Python Code)

Max Activating Token Index: 520

Text #8

Max Range: 3.9514. Min Range: -3.9514

Max Act: 3.8263. Min Act: -0.1700

Data Index: 1630446 (Python Code)

Max Activating Token Index: 996

Text #9

Max Range: 3.9514. Min Range: -3.9514

Max Act: 3.8576. Min Act: -0.1700

Data Index: 1525254 (Python Code)

Max Activating Token Index: 981

Text #10

Max Range: 3.9514. Min Range: -3.9514

Max Act: 3.7950. Min Act: -0.1700

Data Index: 1492966 (Python Code)

Max Activating Token Index: 495

Text #11

Max Range: 3.9514. Min Range: -3.9514

Max Act: 3.8263. Min Act: -0.1700

Data Index: 1632485 (Python Code)

Max Activating Token Index: 966

Text #12

Max Range: 3.9514. Min Range: -3.9514

Max Act: 3.7637. Min Act: -0.1700

Data Index: 1451597 (Python Code)

Max Activating Token Index: 184

Text #13

Max Range: 3.9514. Min Range: -3.9514

Max Act: 3.7950. Min Act: -0.1700

Data Index: 1444200 (Python Code)

Max Activating Token Index: 369

Text #14

Max Range: 3.9514. Min Range: -3.9514

Max Act: 3.7950. Min Act: -0.1700

Data Index: 1643318 (Python Code)

Max Activating Token Index: 546

Text #15

Max Range: 3.9514. Min Range: -3.9514

Max Act: 3.7950. Min Act: -0.1700

Data Index: 1654393 (Python Code)

Max Activating Token Index: 439

Text #16

Max Range: 3.9514. Min Range: -3.9514

Max Act: 3.7950. Min Act: -0.1700

Data Index: 1597395 (Python Code)

Max Activating Token Index: 979

Text #17

Max Range: 3.9514. Min Range: -3.9514

Max Act: 3.7637. Min Act: -0.1700

Data Index: 791334 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 3.9514. Min Range: -3.9514

Max Act: 3.7324. Min Act: -0.1700

Data Index: 1374089 (Python Code)

Max Activating Token Index: 1010

Text #19

Max Range: 3.9514. Min Range: -3.9514

Max Act: 3.7011. Min Act: -0.1700

Data Index: 1560021 (Python Code)

Max Activating Token Index: 393