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

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

Neuron 1141 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: 3.7120. Min Range: -3.7120

Max Act: 3.7120. Min Act: -0.1700

Data Index: 1534324 (Python Code)

Max Activating Token Index: 225

Text #1

Max Range: 3.7120. Min Range: -3.7120

Max Act: 3.5348. Min Act: -0.1700

Data Index: 1501013 (Python Code)

Max Activating Token Index: 890

Text #2

Max Range: 3.7120. Min Range: -3.7120

Max Act: 3.5257. Min Act: -0.1700

Data Index: 1444163 (Python Code)

Max Activating Token Index: 172

Text #3

Max Range: 3.7120. Min Range: -3.7120

Max Act: 3.5074. Min Act: -0.1700

Data Index: 1615278 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 3.7120. Min Range: -3.7120

Max Act: 3.4750. Min Act: -0.1700

Data Index: 1493234 (Python Code)

Max Activating Token Index: 841

Text #5

Max Range: 3.7120. Min Range: -3.7120

Max Act: 3.4867. Min Act: -0.1700

Data Index: 1379381 (Python Code)

Max Activating Token Index: 844

Text #6

Max Range: 3.7120. Min Range: -3.7120

Max Act: 3.4484. Min Act: -0.1700

Data Index: 1365471 (Python Code)

Max Activating Token Index: 622

Text #7

Max Range: 3.7120. Min Range: -3.7120

Max Act: 3.4641. Min Act: -0.1700

Data Index: 1127149 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 3.7120. Min Range: -3.7120

Max Act: 3.4482. Min Act: -0.1700

Data Index: 1621746 (Python Code)

Max Activating Token Index: 804

Text #9

Max Range: 3.7120. Min Range: -3.7120

Max Act: 3.4481. Min Act: -0.1700

Data Index: 1439351 (Python Code)

Max Activating Token Index: 910

Text #10

Max Range: 3.7120. Min Range: -3.7120

Max Act: 3.3910. Min Act: -0.1700

Data Index: 1414592 (Python Code)

Max Activating Token Index: 946

Text #11

Max Range: 3.7120. Min Range: -3.7120

Max Act: 3.3924. Min Act: -0.1692

Data Index: 1539925 (Python Code)

Max Activating Token Index: 40

Text #12

Max Range: 3.7120. Min Range: -3.7120

Max Act: 3.4360. Min Act: -0.1700

Data Index: 1472695 (Python Code)

Max Activating Token Index: 724

Text #13

Max Range: 3.7120. Min Range: -3.7120

Max Act: 3.3640. Min Act: -0.1700

Data Index: 1565577 (Python Code)

Max Activating Token Index: 103

Text #14

Max Range: 3.7120. Min Range: -3.7120

Max Act: 3.3680. Min Act: -0.1700

Data Index: 1633847 (Python Code)

Max Activating Token Index: 778

Text #15

Max Range: 3.7120. Min Range: -3.7120

Max Act: 3.3681. Min Act: -0.1700

Data Index: 1573119 (Python Code)

Max Activating Token Index: 507

Text #16

Max Range: 3.7120. Min Range: -3.7120

Max Act: 3.3787. Min Act: -0.1700

Data Index: 1360803 (Python Code)

Max Activating Token Index: 578

Text #17

Max Range: 3.7120. Min Range: -3.7120

Max Act: 3.3765. Min Act: -0.1700

Data Index: 1425308 (Python Code)

Max Activating Token Index: 553

Text #18

Max Range: 3.7120. Min Range: -3.7120

Max Act: 3.3879. Min Act: -0.1700

Data Index: 1383500 (Python Code)

Max Activating Token Index: 471

Text #19

Max Range: 3.7120. Min Range: -3.7120

Max Act: 3.3387. Min Act: -0.1699

Data Index: 1568962 (Python Code)

Max Activating Token Index: 250