Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1867 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.6311. Min Range: -5.6311

Max Act: 5.5373. Min Act: -0.1700

Data Index: 1457447 (Python Code)

Max Activating Token Index: 69

Text #1

Max Range: 5.6311. Min Range: -5.6311

Max Act: 5.6311. Min Act: -0.1700

Data Index: 1374089 (Python Code)

Max Activating Token Index: 53

Text #2

Max Range: 5.6311. Min Range: -5.6311

Max Act: 5.5686. Min Act: -0.1700

Data Index: 1566935 (Python Code)

Max Activating Token Index: 42

Text #3

Max Range: 5.6311. Min Range: -5.6311

Max Act: 5.4748. Min Act: -0.1700

Data Index: 1509545 (Python Code)

Max Activating Token Index: 153

Text #4

Max Range: 5.6311. Min Range: -5.6311

Max Act: 5.5061. Min Act: -0.1700

Data Index: 1406050 (Python Code)

Max Activating Token Index: 110

Text #5

Max Range: 5.6311. Min Range: -5.6311

Max Act: 5.4436. Min Act: -0.1700

Data Index: 1508952 (Python Code)

Max Activating Token Index: 111

Text #6

Max Range: 5.6311. Min Range: -5.6311

Max Act: 5.5061. Min Act: -0.1700

Data Index: 1630446 (Python Code)

Max Activating Token Index: 89

Text #7

Max Range: 5.6311. Min Range: -5.6311

Max Act: 5.4748. Min Act: -0.1700

Data Index: 1544524 (Python Code)

Max Activating Token Index: 44

Text #8

Max Range: 5.6311. Min Range: -5.6311

Max Act: 5.5373. Min Act: -0.1700

Data Index: 1632485 (Python Code)

Max Activating Token Index: 71

Text #9

Max Range: 5.6311. Min Range: -5.6311

Max Act: 5.3186. Min Act: -0.1700

Data Index: 1507369 (Python Code)

Max Activating Token Index: 801

Text #10

Max Range: 5.6311. Min Range: -5.6311

Max Act: 5.4436. Min Act: -0.1700

Data Index: 1563278 (Python Code)

Max Activating Token Index: 121

Text #11

Max Range: 5.6311. Min Range: -5.6311

Max Act: 5.4123. Min Act: -0.1700

Data Index: 1444395 (Python Code)

Max Activating Token Index: 749

Text #12

Max Range: 5.6311. Min Range: -5.6311

Max Act: 5.3811. Min Act: -0.1700

Data Index: 1519411 (Python Code)

Max Activating Token Index: 103

Text #13

Max Range: 5.6311. Min Range: -5.6311

Max Act: 5.5061. Min Act: -0.1700

Data Index: 1558828 (Python Code)

Max Activating Token Index: 76

Text #14

Max Range: 5.6311. Min Range: -5.6311

Max Act: 5.4123. Min Act: -0.1700

Data Index: 1375714 (Python Code)

Max Activating Token Index: 195

Text #15

Max Range: 5.6311. Min Range: -5.6311

Max Act: 5.4748. Min Act: -0.1700

Data Index: 1416223 (Python Code)

Max Activating Token Index: 626

Text #16

Max Range: 5.6311. Min Range: -5.6311

Max Act: 5.4123. Min Act: -0.1700

Data Index: 1570986 (Python Code)

Max Activating Token Index: 243

Text #17

Max Range: 5.6311. Min Range: -5.6311

Max Act: 5.3186. Min Act: -0.1700

Data Index: 1389220 (Python Code)

Max Activating Token Index: 107

Text #18

Max Range: 5.6311. Min Range: -5.6311

Max Act: 5.4123. Min Act: -0.1700

Data Index: 1566682 (Python Code)

Max Activating Token Index: 143

Text #19

Max Range: 5.6311. Min Range: -5.6311

Max Act: 5.3186. Min Act: -0.1700

Data Index: 1361929 (Python Code)

Max Activating Token Index: 198