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

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

Neuron 443 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: 3.3747. Min Range: -3.3747

Max Act: 3.3747. Min Act: -0.1700

Data Index: 1378789 (Python Code)

Max Activating Token Index: 770

Text #1

Max Range: 3.3747. Min Range: -3.3747

Max Act: 3.3433. Min Act: -0.1700

Data Index: 1513304 (Python Code)

Max Activating Token Index: 23

Text #2

Max Range: 3.3747. Min Range: -3.3747

Max Act: 3.3433. Min Act: -0.1700

Data Index: 1536380 (Python Code)

Max Activating Token Index: 863

Text #3

Max Range: 3.3747. Min Range: -3.3747

Max Act: 3.3119. Min Act: -0.1700

Data Index: 1506810 (Python Code)

Max Activating Token Index: 66

Text #4

Max Range: 3.3747. Min Range: -3.3747

Max Act: 3.3433. Min Act: -0.1700

Data Index: 1601186 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.3747. Min Range: -3.3747

Max Act: 3.3276. Min Act: -0.1700

Data Index: 1499847 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 3.3747. Min Range: -3.3747

Max Act: 3.3119. Min Act: -0.1700

Data Index: 1419434 (Python Code)

Max Activating Token Index: 92

Text #7

Max Range: 3.3747. Min Range: -3.3747

Max Act: 3.3276. Min Act: -0.1700

Data Index: 1545956 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 3.3747. Min Range: -3.3747

Max Act: 3.3119. Min Act: -0.1700

Data Index: 1441939 (Python Code)

Max Activating Token Index: 645

Text #9

Max Range: 3.3747. Min Range: -3.3747

Max Act: 3.2962. Min Act: -0.1700

Data Index: 1627989 (Python Code)

Max Activating Token Index: 478

Text #10

Max Range: 3.3747. Min Range: -3.3747

Max Act: 3.2962. Min Act: -0.1700

Data Index: 1570613 (Python Code)

Max Activating Token Index: 425

Text #11

Max Range: 3.3747. Min Range: -3.3747

Max Act: 3.3119. Min Act: -0.1700

Data Index: 1451446 (Python Code)

Max Activating Token Index: 191

Text #12

Max Range: 3.3747. Min Range: -3.3747

Max Act: 3.3119. Min Act: -0.1700

Data Index: 1492185 (Python Code)

Max Activating Token Index: 50

Text #13

Max Range: 3.3747. Min Range: -3.3747

Max Act: 3.2962. Min Act: -0.1700

Data Index: 1599154 (Python Code)

Max Activating Token Index: 61

Text #14

Max Range: 3.3747. Min Range: -3.3747

Max Act: 3.2805. Min Act: -0.1700

Data Index: 1496180 (Python Code)

Max Activating Token Index: 338

Text #15

Max Range: 3.3747. Min Range: -3.3747

Max Act: 3.2805. Min Act: -0.1700

Data Index: 1475286 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 3.3747. Min Range: -3.3747

Max Act: 3.2962. Min Act: -0.1700

Data Index: 1631008 (Python Code)

Max Activating Token Index: 53

Text #17

Max Range: 3.3747. Min Range: -3.3747

Max Act: 3.2491. Min Act: -0.1700

Data Index: 1500153 (Python Code)

Max Activating Token Index: 543

Text #18

Max Range: 3.3747. Min Range: -3.3747

Max Act: 3.2805. Min Act: -0.1700

Data Index: 1571604 (Python Code)

Max Activating Token Index: 183

Text #19

Max Range: 3.3747. Min Range: -3.3747

Max Act: 3.2648. Min Act: -0.1700

Data Index: 1553361 (Python Code)

Max Activating Token Index: 98