Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 15 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.4938. Min Range: -5.4938

Max Act: 5.4938. Min Act: -0.1699

Data Index: 1469987 (Python Code)

Max Activating Token Index: 314

Text #1

Max Range: 5.4938. Min Range: -5.4938

Max Act: 5.4313. Min Act: -0.1700

Data Index: 1643887 (Python Code)

Max Activating Token Index: 495

Text #2

Max Range: 5.4938. Min Range: -5.4938

Max Act: 5.4625. Min Act: -0.1700

Data Index: 1531507 (Python Code)

Max Activating Token Index: 770

Text #3

Max Range: 5.4938. Min Range: -5.4938

Max Act: 5.4000. Min Act: -0.1700

Data Index: 1654742 (Python Code)

Max Activating Token Index: 870

Text #4

Max Range: 5.4938. Min Range: -5.4938

Max Act: 5.3688. Min Act: -0.1700

Data Index: 1626572 (Python Code)

Max Activating Token Index: 565

Text #5

Max Range: 5.4938. Min Range: -5.4938

Max Act: 5.3063. Min Act: -0.1700

Data Index: 1449535 (Python Code)

Max Activating Token Index: 373

Text #6

Max Range: 5.4938. Min Range: -5.4938

Max Act: 5.2750. Min Act: -0.1700

Data Index: 1651311 (Python Code)

Max Activating Token Index: 482

Text #7

Max Range: 5.4938. Min Range: -5.4938

Max Act: 5.3063. Min Act: -0.1700

Data Index: 1611741 (Python Code)

Max Activating Token Index: 647

Text #8

Max Range: 5.4938. Min Range: -5.4938

Max Act: 5.3063. Min Act: -0.1700

Data Index: 1589987 (Python Code)

Max Activating Token Index: 383

Text #9

Max Range: 5.4938. Min Range: -5.4938

Max Act: 5.3063. Min Act: -0.1700

Data Index: 1370037 (Python Code)

Max Activating Token Index: 155

Text #10

Max Range: 5.4938. Min Range: -5.4938

Max Act: 5.2125. Min Act: -0.1699

Data Index: 1502419 (Python Code)

Max Activating Token Index: 341

Text #11

Max Range: 5.4938. Min Range: -5.4938

Max Act: 5.1500. Min Act: -0.1700

Data Index: 1362213 (Python Code)

Max Activating Token Index: 759

Text #12

Max Range: 5.4938. Min Range: -5.4938

Max Act: 5.2750. Min Act: -0.1700

Data Index: 1413934 (Python Code)

Max Activating Token Index: 216

Text #13

Max Range: 5.4938. Min Range: -5.4938

Max Act: 5.2750. Min Act: -0.1700

Data Index: 1607484 (Python Code)

Max Activating Token Index: 839

Text #14

Max Range: 5.4938. Min Range: -5.4938

Max Act: 5.2438. Min Act: -0.1699

Data Index: 1369348 (Python Code)

Max Activating Token Index: 422

Text #15

Max Range: 5.4938. Min Range: -5.4938

Max Act: 5.2750. Min Act: -0.1700

Data Index: 1571663 (Python Code)

Max Activating Token Index: 640

Text #16

Max Range: 5.4938. Min Range: -5.4938

Max Act: 5.2125. Min Act: -0.1700

Data Index: 1564729 (Python Code)

Max Activating Token Index: 336

Text #17

Max Range: 5.4938. Min Range: -5.4938

Max Act: 5.1813. Min Act: -0.1699

Data Index: 1551566 (Python Code)

Max Activating Token Index: 241

Text #18

Max Range: 5.4938. Min Range: -5.4938

Max Act: 5.1813. Min Act: -0.1700

Data Index: 1649569 (Python Code)

Max Activating Token Index: 344

Text #19

Max Range: 5.4938. Min Range: -5.4938

Max Act: 5.2750. Min Act: -0.1700

Data Index: 1539809 (Python Code)

Max Activating Token Index: 801