Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1677 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.4552. Min Range: -3.4552

Max Act: 3.4552. Min Act: -0.1700

Data Index: 1594010 (Python Code)

Max Activating Token Index: 417

Text #1

Max Range: 3.4552. Min Range: -3.4552

Max Act: 3.3753. Min Act: -0.1700

Data Index: 1514168 (Python Code)

Max Activating Token Index: 283

Text #2

Max Range: 3.4552. Min Range: -3.4552

Max Act: 3.2862. Min Act: -0.1700

Data Index: 1652358 (Python Code)

Max Activating Token Index: 165

Text #3

Max Range: 3.4552. Min Range: -3.4552

Max Act: 3.2563. Min Act: -0.1700

Data Index: 1635566 (Python Code)

Max Activating Token Index: 424

Text #4

Max Range: 3.4552. Min Range: -3.4552

Max Act: 3.2656. Min Act: -0.1700

Data Index: 1613362 (Python Code)

Max Activating Token Index: 372

Text #5

Max Range: 3.4552. Min Range: -3.4552

Max Act: 3.2336. Min Act: -0.1700

Data Index: 1632931 (Python Code)

Max Activating Token Index: 109

Text #6

Max Range: 3.4552. Min Range: -3.4552

Max Act: 3.1910. Min Act: -0.1700

Data Index: 1617708 (Python Code)

Max Activating Token Index: 969

Text #7

Max Range: 3.4552. Min Range: -3.4552

Max Act: 3.2110. Min Act: -0.1700

Data Index: 1434305 (Python Code)

Max Activating Token Index: 121

Text #8

Max Range: 3.4552. Min Range: -3.4552

Max Act: 3.1723. Min Act: -0.1700

Data Index: 1463870 (Python Code)

Max Activating Token Index: 217

Text #9

Max Range: 3.4552. Min Range: -3.4552

Max Act: 3.1880. Min Act: -0.1700

Data Index: 1459276 (Python Code)

Max Activating Token Index: 465

Text #10

Max Range: 3.4552. Min Range: -3.4552

Max Act: 3.1782. Min Act: -0.1700

Data Index: 1525702 (Python Code)

Max Activating Token Index: 54

Text #11

Max Range: 3.4552. Min Range: -3.4552

Max Act: 3.1692. Min Act: -0.1700

Data Index: 1652388 (Python Code)

Max Activating Token Index: 96

Text #12

Max Range: 3.4552. Min Range: -3.4552

Max Act: 3.1696. Min Act: -0.1700

Data Index: 1391328 (Python Code)

Max Activating Token Index: 354

Text #13

Max Range: 3.4552. Min Range: -3.4552

Max Act: 3.1438. Min Act: -0.1700

Data Index: 1436233 (Python Code)

Max Activating Token Index: 48

Text #14

Max Range: 3.4552. Min Range: -3.4552

Max Act: 3.1454. Min Act: -0.1700

Data Index: 1390426 (Python Code)

Max Activating Token Index: 720

Text #15

Max Range: 3.4552. Min Range: -3.4552

Max Act: 3.1224. Min Act: -0.1700

Data Index: 1630990 (Python Code)

Max Activating Token Index: 852

Text #16

Max Range: 3.4552. Min Range: -3.4552

Max Act: 3.1475. Min Act: -0.1699

Data Index: 1423976 (Python Code)

Max Activating Token Index: 498

Text #17

Max Range: 3.4552. Min Range: -3.4552

Max Act: 3.1417. Min Act: -0.1700

Data Index: 833631 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 3.4552. Min Range: -3.4552

Max Act: 3.1183. Min Act: -0.1700

Data Index: 1594378 (Python Code)

Max Activating Token Index: 139

Text #19

Max Range: 3.4552. Min Range: -3.4552

Max Act: 3.1153. Min Act: -0.1700

Data Index: 1456813 (Python Code)

Max Activating Token Index: 549