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

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

Neuron 475 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: 3.4530. Min Range: -3.4530

Max Act: 3.4530. Min Act: -0.1700

Data Index: 1471380 (Python Code)

Max Activating Token Index: 890

Text #1

Max Range: 3.4530. Min Range: -3.4530

Max Act: 3.3828. Min Act: -0.1700

Data Index: 1521470 (Python Code)

Max Activating Token Index: 824

Text #2

Max Range: 3.4530. Min Range: -3.4530

Max Act: 3.3789. Min Act: -0.1700

Data Index: 1493797 (Python Code)

Max Activating Token Index: 791

Text #3

Max Range: 3.4530. Min Range: -3.4530

Max Act: 3.2793. Min Act: -0.1700

Data Index: 1598909 (Python Code)

Max Activating Token Index: 1008

Text #4

Max Range: 3.4530. Min Range: -3.4530

Max Act: 3.2684. Min Act: -0.1700

Data Index: 1425860 (Python Code)

Max Activating Token Index: 478

Text #5

Max Range: 3.4530. Min Range: -3.4530

Max Act: 3.2694. Min Act: -0.1700

Data Index: 1451295 (Python Code)

Max Activating Token Index: 192

Text #6

Max Range: 3.4530. Min Range: -3.4530

Max Act: 3.2500. Min Act: -0.1700

Data Index: 1628901 (Python Code)

Max Activating Token Index: 848

Text #7

Max Range: 3.4530. Min Range: -3.4530

Max Act: 3.2554. Min Act: -0.1700

Data Index: 1385424 (Python Code)

Max Activating Token Index: 703

Text #8

Max Range: 3.4530. Min Range: -3.4530

Max Act: 3.2012. Min Act: -0.1700

Data Index: 1380202 (Python Code)

Max Activating Token Index: 486

Text #9

Max Range: 3.4530. Min Range: -3.4530

Max Act: 3.2101. Min Act: -0.1700

Data Index: 1450629 (Python Code)

Max Activating Token Index: 253

Text #10

Max Range: 3.4530. Min Range: -3.4530

Max Act: 3.1949. Min Act: -0.1700

Data Index: 1397275 (Python Code)

Max Activating Token Index: 959

Text #11

Max Range: 3.4530. Min Range: -3.4530

Max Act: 3.1767. Min Act: -0.1700

Data Index: 1365494 (Python Code)

Max Activating Token Index: 617

Text #12

Max Range: 3.4530. Min Range: -3.4530

Max Act: 3.1676. Min Act: -0.1700

Data Index: 1604569 (Python Code)

Max Activating Token Index: 755

Text #13

Max Range: 3.4530. Min Range: -3.4530

Max Act: 3.1705. Min Act: -0.1700

Data Index: 1633313 (Python Code)

Max Activating Token Index: 817

Text #14

Max Range: 3.4530. Min Range: -3.4530

Max Act: 3.1518. Min Act: -0.1700

Data Index: 1549176 (Python Code)

Max Activating Token Index: 823

Text #15

Max Range: 3.4530. Min Range: -3.4530

Max Act: 3.1518. Min Act: -0.1700

Data Index: 1567839 (Python Code)

Max Activating Token Index: 41

Text #16

Max Range: 3.4530. Min Range: -3.4530

Max Act: 3.1594. Min Act: -0.1700

Data Index: 1424172 (Python Code)

Max Activating Token Index: 939

Text #17

Max Range: 3.4530. Min Range: -3.4530

Max Act: 3.1435. Min Act: -0.1700

Data Index: 1492358 (Python Code)

Max Activating Token Index: 782

Text #18

Max Range: 3.4530. Min Range: -3.4530

Max Act: 3.1353. Min Act: -0.1700

Data Index: 1473272 (Python Code)

Max Activating Token Index: 891

Text #19

Max Range: 3.4530. Min Range: -3.4530

Max Act: 3.1365. Min Act: -0.1700

Data Index: 399931 (C4 (Web Text))

Max Activating Token Index: 743