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

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

Neuron 1204 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: 3.8413. Min Range: -3.8413

Max Act: 3.8413. Min Act: -0.1700

Data Index: 780643 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.8413. Min Act: -0.1700

Data Index: 1387384 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.7787. Min Act: -0.1700

Data Index: 1501510 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.7162. Min Act: -0.1700

Data Index: 450136 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.7162. Min Act: -0.1700

Data Index: 1648851 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.7475. Min Act: -0.1700

Data Index: 1606092 (Python Code)

Max Activating Token Index: 550

Text #6

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.7162. Min Act: -0.1700

Data Index: 1584185 (Python Code)

Max Activating Token Index: 754

Text #7

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6849. Min Act: -0.1700

Data Index: 1124627 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.7162. Min Act: -0.1700

Data Index: 1416855 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6849. Min Act: -0.1700

Data Index: 1499447 (Python Code)

Max Activating Token Index: 453

Text #10

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6849. Min Act: -0.1700

Data Index: 1410540 (Python Code)

Max Activating Token Index: 833

Text #11

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6849. Min Act: -0.1700

Data Index: 1465435 (Python Code)

Max Activating Token Index: 709

Text #12

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6849. Min Act: -0.1700

Data Index: 1603865 (Python Code)

Max Activating Token Index: 341

Text #13

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6536. Min Act: -0.1700

Data Index: 1553750 (Python Code)

Max Activating Token Index: 702

Text #14

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6536. Min Act: -0.1700

Data Index: 1468795 (Python Code)

Max Activating Token Index: 585

Text #15

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6849. Min Act: -0.1700

Data Index: 1465114 (Python Code)

Max Activating Token Index: 503

Text #16

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6536. Min Act: -0.1700

Data Index: 1408795 (Python Code)

Max Activating Token Index: 707

Text #17

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6536. Min Act: -0.1700

Data Index: 1478271 (Python Code)

Max Activating Token Index: 396

Text #18

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6536. Min Act: -0.1700

Data Index: 1385779 (Python Code)

Max Activating Token Index: 926

Text #19

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6223. Min Act: -0.1700

Data Index: 1463153 (Python Code)

Max Activating Token Index: 606