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

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

Neuron 1994 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: 3.3735. Min Range: -3.3735

Max Act: 3.3735. Min Act: -0.1700

Data Index: 1522346 (Python Code)

Max Activating Token Index: 703

Text #1

Max Range: 3.3735. Min Range: -3.3735

Max Act: 3.3454. Min Act: -0.1700

Data Index: 1551280 (Python Code)

Max Activating Token Index: 913

Text #2

Max Range: 3.3735. Min Range: -3.3735

Max Act: 3.2795. Min Act: -0.1700

Data Index: 1505716 (Python Code)

Max Activating Token Index: 772

Text #3

Max Range: 3.3735. Min Range: -3.3735

Max Act: 3.2813. Min Act: -0.1700

Data Index: 1655176 (Python Code)

Max Activating Token Index: 570

Text #4

Max Range: 3.3735. Min Range: -3.3735

Max Act: 3.2529. Min Act: -0.1700

Data Index: 1638795 (Python Code)

Max Activating Token Index: 685

Text #5

Max Range: 3.3735. Min Range: -3.3735

Max Act: 3.2690. Min Act: -0.1700

Data Index: 1621610 (Python Code)

Max Activating Token Index: 719

Text #6

Max Range: 3.3735. Min Range: -3.3735

Max Act: 3.2446. Min Act: -0.1700

Data Index: 1399810 (Python Code)

Max Activating Token Index: 754

Text #7

Max Range: 3.3735. Min Range: -3.3735

Max Act: 3.2656. Min Act: -0.1700

Data Index: 1424751 (Python Code)

Max Activating Token Index: 173

Text #8

Max Range: 3.3735. Min Range: -3.3735

Max Act: 3.2251. Min Act: -0.1700

Data Index: 1535855 (Python Code)

Max Activating Token Index: 438

Text #9

Max Range: 3.3735. Min Range: -3.3735

Max Act: 3.2117. Min Act: -0.1700

Data Index: 1475237 (Python Code)

Max Activating Token Index: 976

Text #10

Max Range: 3.3735. Min Range: -3.3735

Max Act: 3.2195. Min Act: -0.1700

Data Index: 1530272 (Python Code)

Max Activating Token Index: 622

Text #11

Max Range: 3.3735. Min Range: -3.3735

Max Act: 3.2200. Min Act: -0.1700

Data Index: 1373426 (Python Code)

Max Activating Token Index: 889

Text #12

Max Range: 3.3735. Min Range: -3.3735

Max Act: 3.2100. Min Act: -0.1700

Data Index: 1547155 (Python Code)

Max Activating Token Index: 165

Text #13

Max Range: 3.3735. Min Range: -3.3735

Max Act: 3.1985. Min Act: -0.1700

Data Index: 1539678 (Python Code)

Max Activating Token Index: 713

Text #14

Max Range: 3.3735. Min Range: -3.3735

Max Act: 3.2170. Min Act: -0.1700

Data Index: 1547500 (Python Code)

Max Activating Token Index: 718

Text #15

Max Range: 3.3735. Min Range: -3.3735

Max Act: 3.1771. Min Act: -0.1700

Data Index: 1540691 (Python Code)

Max Activating Token Index: 369

Text #16

Max Range: 3.3735. Min Range: -3.3735

Max Act: 3.1806. Min Act: -0.1700

Data Index: 1629565 (Python Code)

Max Activating Token Index: 207

Text #17

Max Range: 3.3735. Min Range: -3.3735

Max Act: 3.1794. Min Act: -0.1700

Data Index: 1496306 (Python Code)

Max Activating Token Index: 913

Text #18

Max Range: 3.3735. Min Range: -3.3735

Max Act: 3.1657. Min Act: -0.1700

Data Index: 1373321 (Python Code)

Max Activating Token Index: 953

Text #19

Max Range: 3.3735. Min Range: -3.3735

Max Act: 3.1733. Min Act: -0.1700

Data Index: 1629911 (Python Code)

Max Activating Token Index: 919