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

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

Neuron 505 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: 3.8268. Min Range: -3.8268

Max Act: 3.8268. Min Act: -0.1700

Data Index: 482942 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.6547. Min Act: -0.1700

Data Index: 863409 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.6077. Min Act: -0.1700

Data Index: 1632029 (Python Code)

Max Activating Token Index: 606

Text #3

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.6390. Min Act: -0.1700

Data Index: 1261076 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.6077. Min Act: -0.1700

Data Index: 1636337 (Python Code)

Max Activating Token Index: 620

Text #5

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.6234. Min Act: -0.1700

Data Index: 1240441 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.6547. Min Act: -0.1700

Data Index: 1609086 (Python Code)

Max Activating Token Index: 944

Text #7

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.6077. Min Act: -0.1700

Data Index: 137527 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.5764. Min Act: -0.1700

Data Index: 1476073 (Python Code)

Max Activating Token Index: 652

Text #9

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.6077. Min Act: -0.1700

Data Index: 1491885 (Python Code)

Max Activating Token Index: 561

Text #10

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.5921. Min Act: -0.1700

Data Index: 1427165 (Python Code)

Max Activating Token Index: 760

Text #11

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.5607. Min Act: -0.1700

Data Index: 1373410 (Python Code)

Max Activating Token Index: 897

Text #12

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.5607. Min Act: -0.1700

Data Index: 1460237 (Python Code)

Max Activating Token Index: 744

Text #13

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.5764. Min Act: -0.1700

Data Index: 1136827 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.5137. Min Act: -0.1700

Data Index: 1482787 (Python Code)

Max Activating Token Index: 510

Text #15

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.5607. Min Act: -0.1700

Data Index: 1154093 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.5137. Min Act: -0.1700

Data Index: 1455723 (Python Code)

Max Activating Token Index: 396

Text #17

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.5764. Min Act: -0.1700

Data Index: 1593891 (Python Code)

Max Activating Token Index: 276

Text #18

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.5294. Min Act: -0.1700

Data Index: 1510517 (Python Code)

Max Activating Token Index: 755

Text #19

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.5607. Min Act: -0.1700

Data Index: 1608066 (Python Code)

Max Activating Token Index: 793