Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1434 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.5741. Min Range: -5.5741

Max Act: 5.5116. Min Act: -0.1700

Data Index: 1398076 (Python Code)

Max Activating Token Index: 1021

Text #1

Max Range: 5.5741. Min Range: -5.5741

Max Act: 5.5741. Min Act: -0.1700

Data Index: 1493550 (Python Code)

Max Activating Token Index: 932

Text #2

Max Range: 5.5741. Min Range: -5.5741

Max Act: 5.4179. Min Act: -0.1700

Data Index: 1508203 (Python Code)

Max Activating Token Index: 167

Text #3

Max Range: 5.5741. Min Range: -5.5741

Max Act: 5.3866. Min Act: -0.1700

Data Index: 1423644 (Python Code)

Max Activating Token Index: 393

Text #4

Max Range: 5.5741. Min Range: -5.5741

Max Act: 5.3554. Min Act: -0.1700

Data Index: 1395553 (Python Code)

Max Activating Token Index: 973

Text #5

Max Range: 5.5741. Min Range: -5.5741

Max Act: 5.4179. Min Act: -0.1700

Data Index: 1524372 (Python Code)

Max Activating Token Index: 261

Text #6

Max Range: 5.5741. Min Range: -5.5741

Max Act: 5.4179. Min Act: -0.1700

Data Index: 1389446 (Python Code)

Max Activating Token Index: 260

Text #7

Max Range: 5.5741. Min Range: -5.5741

Max Act: 5.3554. Min Act: -0.1700

Data Index: 1621216 (Python Code)

Max Activating Token Index: 812

Text #8

Max Range: 5.5741. Min Range: -5.5741

Max Act: 5.3241. Min Act: -0.1700

Data Index: 1453581 (Python Code)

Max Activating Token Index: 1018

Text #9

Max Range: 5.5741. Min Range: -5.5741

Max Act: 5.3554. Min Act: -0.1700

Data Index: 1575305 (Python Code)

Max Activating Token Index: 70

Text #10

Max Range: 5.5741. Min Range: -5.5741

Max Act: 5.3241. Min Act: -0.1700

Data Index: 1535510 (Python Code)

Max Activating Token Index: 295

Text #11

Max Range: 5.5741. Min Range: -5.5741

Max Act: 5.3398. Min Act: -0.1700

Data Index: 1492313 (Python Code)

Max Activating Token Index: 852

Text #12

Max Range: 5.5741. Min Range: -5.5741

Max Act: 5.3085. Min Act: -0.1700

Data Index: 1421577 (Python Code)

Max Activating Token Index: 1001

Text #13

Max Range: 5.5741. Min Range: -5.5741

Max Act: 5.3398. Min Act: -0.1700

Data Index: 1432258 (Python Code)

Max Activating Token Index: 117

Text #14

Max Range: 5.5741. Min Range: -5.5741

Max Act: 5.2929. Min Act: -0.1700

Data Index: 1364475 (Python Code)

Max Activating Token Index: 927

Text #15

Max Range: 5.5741. Min Range: -5.5741

Max Act: 5.2773. Min Act: -0.1700

Data Index: 1446379 (Python Code)

Max Activating Token Index: 167

Text #16

Max Range: 5.5741. Min Range: -5.5741

Max Act: 5.3398. Min Act: -0.1700

Data Index: 1464312 (Python Code)

Max Activating Token Index: 1001

Text #17

Max Range: 5.5741. Min Range: -5.5741

Max Act: 5.3241. Min Act: -0.1700

Data Index: 1565275 (Python Code)

Max Activating Token Index: 161

Text #18

Max Range: 5.5741. Min Range: -5.5741

Max Act: 5.2773. Min Act: -0.1700

Data Index: 1577031 (Python Code)

Max Activating Token Index: 449

Text #19

Max Range: 5.5741. Min Range: -5.5741

Max Act: 5.2929. Min Act: -0.1700

Data Index: 1412852 (Python Code)

Max Activating Token Index: 917