Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 552 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8800. Min Range: -3.8800

Max Act: 3.8800. Min Act: -0.1700

Data Index: 1415377 (Python Code)

Max Activating Token Index: 839

Text #1

Max Range: 3.8800. Min Range: -3.8800

Max Act: 3.8487. Min Act: -0.1696

Data Index: 1385074 (Python Code)

Max Activating Token Index: 548

Text #2

Max Range: 3.8800. Min Range: -3.8800

Max Act: 3.7862. Min Act: -0.1699

Data Index: 1520262 (Python Code)

Max Activating Token Index: 395

Text #3

Max Range: 3.8800. Min Range: -3.8800

Max Act: 3.6923. Min Act: -0.1700

Data Index: 1410580 (Python Code)

Max Activating Token Index: 224

Text #4

Max Range: 3.8800. Min Range: -3.8800

Max Act: 3.6610. Min Act: -0.1699

Data Index: 1390657 (Python Code)

Max Activating Token Index: 549

Text #5

Max Range: 3.8800. Min Range: -3.8800

Max Act: 3.6610. Min Act: -0.1700

Data Index: 1410948 (Python Code)

Max Activating Token Index: 1005

Text #6

Max Range: 3.8800. Min Range: -3.8800

Max Act: 3.6610. Min Act: -0.1700

Data Index: 1461997 (Python Code)

Max Activating Token Index: 325

Text #7

Max Range: 3.8800. Min Range: -3.8800

Max Act: 3.6297. Min Act: -0.1700

Data Index: 1514045 (Python Code)

Max Activating Token Index: 351

Text #8

Max Range: 3.8800. Min Range: -3.8800

Max Act: 3.6297. Min Act: -0.1699

Data Index: 1589493 (Python Code)

Max Activating Token Index: 896

Text #9

Max Range: 3.8800. Min Range: -3.8800

Max Act: 3.6297. Min Act: -0.1699

Data Index: 1452545 (Python Code)

Max Activating Token Index: 921

Text #10

Max Range: 3.8800. Min Range: -3.8800

Max Act: 3.6297. Min Act: -0.1699

Data Index: 1406282 (Python Code)

Max Activating Token Index: 869

Text #11

Max Range: 3.8800. Min Range: -3.8800

Max Act: 3.5984. Min Act: -0.1700

Data Index: 1392514 (Python Code)

Max Activating Token Index: 631

Text #12

Max Range: 3.8800. Min Range: -3.8800

Max Act: 3.5357. Min Act: -0.1699

Data Index: 1393006 (Python Code)

Max Activating Token Index: 420

Text #13

Max Range: 3.8800. Min Range: -3.8800

Max Act: 3.5984. Min Act: -0.1700

Data Index: 1596230 (Python Code)

Max Activating Token Index: 88

Text #14

Max Range: 3.8800. Min Range: -3.8800

Max Act: 3.6297. Min Act: -0.1699

Data Index: 1518013 (Python Code)

Max Activating Token Index: 530

Text #15

Max Range: 3.8800. Min Range: -3.8800

Max Act: 3.5671. Min Act: -0.1700

Data Index: 1490663 (Python Code)

Max Activating Token Index: 294

Text #16

Max Range: 3.8800. Min Range: -3.8800

Max Act: 3.5984. Min Act: -0.1700

Data Index: 1574075 (Python Code)

Max Activating Token Index: 97

Text #17

Max Range: 3.8800. Min Range: -3.8800

Max Act: 3.5671. Min Act: -0.1700

Data Index: 1605812 (Python Code)

Max Activating Token Index: 896

Text #18

Max Range: 3.8800. Min Range: -3.8800

Max Act: 3.5357. Min Act: -0.1700

Data Index: 1628273 (Python Code)

Max Activating Token Index: 429

Text #19

Max Range: 3.8800. Min Range: -3.8800

Max Act: 3.5671. Min Act: -0.1700

Data Index: 1635621 (Python Code)

Max Activating Token Index: 154