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

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

Neuron 973 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: 3.8091. Min Range: -3.8091

Max Act: 3.8091. Min Act: -0.1700

Data Index: 1393945 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 3.8091. Min Range: -3.8091

Max Act: 3.7464. Min Act: -0.1700

Data Index: 1466648 (Python Code)

Max Activating Token Index: 675

Text #2

Max Range: 3.8091. Min Range: -3.8091

Max Act: 3.7267. Min Act: -0.1700

Data Index: 1641652 (Python Code)

Max Activating Token Index: 377

Text #3

Max Range: 3.8091. Min Range: -3.8091

Max Act: 3.6782. Min Act: -0.1700

Data Index: 1621840 (Python Code)

Max Activating Token Index: 42

Text #4

Max Range: 3.8091. Min Range: -3.8091

Max Act: 3.6438. Min Act: -0.1700

Data Index: 1592546 (Python Code)

Max Activating Token Index: 55

Text #5

Max Range: 3.8091. Min Range: -3.8091

Max Act: 3.6542. Min Act: -0.1700

Data Index: 1531617 (Python Code)

Max Activating Token Index: 809

Text #6

Max Range: 3.8091. Min Range: -3.8091

Max Act: 3.6433. Min Act: -0.1700

Data Index: 1513975 (Python Code)

Max Activating Token Index: 876

Text #7

Max Range: 3.8091. Min Range: -3.8091

Max Act: 3.6423. Min Act: -0.1700

Data Index: 1385133 (Python Code)

Max Activating Token Index: 435

Text #8

Max Range: 3.8091. Min Range: -3.8091

Max Act: 3.6291. Min Act: -0.1700

Data Index: 1479642 (Python Code)

Max Activating Token Index: 73

Text #9

Max Range: 3.8091. Min Range: -3.8091

Max Act: 3.6456. Min Act: -0.1700

Data Index: 1382898 (Python Code)

Max Activating Token Index: 564

Text #10

Max Range: 3.8091. Min Range: -3.8091

Max Act: 3.6360. Min Act: -0.1700

Data Index: 1524320 (Python Code)

Max Activating Token Index: 852

Text #11

Max Range: 3.8091. Min Range: -3.8091

Max Act: 3.5930. Min Act: -0.1700

Data Index: 1622117 (Python Code)

Max Activating Token Index: 110

Text #12

Max Range: 3.8091. Min Range: -3.8091

Max Act: 3.6039. Min Act: -0.1700

Data Index: 1526732 (Python Code)

Max Activating Token Index: 831

Text #13

Max Range: 3.8091. Min Range: -3.8091

Max Act: 3.6003. Min Act: -0.1700

Data Index: 1625340 (Python Code)

Max Activating Token Index: 524

Text #14

Max Range: 3.8091. Min Range: -3.8091

Max Act: 3.6081. Min Act: -0.1700

Data Index: 1545633 (Python Code)

Max Activating Token Index: 730

Text #15

Max Range: 3.8091. Min Range: -3.8091

Max Act: 3.5823. Min Act: -0.1700

Data Index: 1545246 (Python Code)

Max Activating Token Index: 140

Text #16

Max Range: 3.8091. Min Range: -3.8091

Max Act: 3.5734. Min Act: -0.1700

Data Index: 1615640 (Python Code)

Max Activating Token Index: 111

Text #17

Max Range: 3.8091. Min Range: -3.8091

Max Act: 3.5648. Min Act: -0.1700

Data Index: 1394657 (Python Code)

Max Activating Token Index: 291

Text #18

Max Range: 3.8091. Min Range: -3.8091

Max Act: 3.5601. Min Act: -0.1700

Data Index: 1538649 (Python Code)

Max Activating Token Index: 36

Text #19

Max Range: 3.8091. Min Range: -3.8091

Max Act: 3.5621. Min Act: -0.1700

Data Index: 1452199 (Python Code)

Max Activating Token Index: 168