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

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

Neuron 1849 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9220. Min Range: -3.9220

Max Act: 3.8907. Min Act: -0.1700

Data Index: 809239 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 3.9220. Min Range: -3.9220

Max Act: 3.9220. Min Act: -0.1700

Data Index: 1489231 (Python Code)

Max Activating Token Index: 795

Text #2

Max Range: 3.9220. Min Range: -3.9220

Max Act: 3.8594. Min Act: -0.1700

Data Index: 1648398 (Python Code)

Max Activating Token Index: 696

Text #3

Max Range: 3.9220. Min Range: -3.9220

Max Act: 3.7969. Min Act: -0.1700

Data Index: 469617 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 3.9220. Min Range: -3.9220

Max Act: 3.7969. Min Act: -0.1700

Data Index: 1444263 (Python Code)

Max Activating Token Index: 854

Text #5

Max Range: 3.9220. Min Range: -3.9220

Max Act: 3.7969. Min Act: -0.1700

Data Index: 1633194 (Python Code)

Max Activating Token Index: 222

Text #6

Max Range: 3.9220. Min Range: -3.9220

Max Act: 3.7656. Min Act: -0.1700

Data Index: 1863 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 3.9220. Min Range: -3.9220

Max Act: 3.7656. Min Act: -0.1700

Data Index: 1394288 (Python Code)

Max Activating Token Index: 747

Text #8

Max Range: 3.9220. Min Range: -3.9220

Max Act: 3.7343. Min Act: -0.1700

Data Index: 1591652 (Python Code)

Max Activating Token Index: 794

Text #9

Max Range: 3.9220. Min Range: -3.9220

Max Act: 3.7656. Min Act: -0.1700

Data Index: 1608087 (Python Code)

Max Activating Token Index: 380

Text #10

Max Range: 3.9220. Min Range: -3.9220

Max Act: 3.7343. Min Act: -0.1700

Data Index: 1439513 (Python Code)

Max Activating Token Index: 100

Text #11

Max Range: 3.9220. Min Range: -3.9220

Max Act: 3.7343. Min Act: -0.1700

Data Index: 1452214 (Python Code)

Max Activating Token Index: 42

Text #12

Max Range: 3.9220. Min Range: -3.9220

Max Act: 3.7343. Min Act: -0.1700

Data Index: 809489 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 3.9220. Min Range: -3.9220

Max Act: 3.7030. Min Act: -0.1700

Data Index: 622237 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 3.9220. Min Range: -3.9220

Max Act: 3.7969. Min Act: -0.1700

Data Index: 1492549 (Python Code)

Max Activating Token Index: 935

Text #15

Max Range: 3.9220. Min Range: -3.9220

Max Act: 3.7030. Min Act: -0.1700

Data Index: 1455882 (Python Code)

Max Activating Token Index: 143

Text #16

Max Range: 3.9220. Min Range: -3.9220

Max Act: 3.7656. Min Act: -0.1700

Data Index: 1413211 (Python Code)

Max Activating Token Index: 874

Text #17

Max Range: 3.9220. Min Range: -3.9220

Max Act: 3.7030. Min Act: -0.1700

Data Index: 1533976 (Python Code)

Max Activating Token Index: 659

Text #18

Max Range: 3.9220. Min Range: -3.9220

Max Act: 3.7030. Min Act: -0.1700

Data Index: 1505687 (Python Code)

Max Activating Token Index: 84

Text #19

Max Range: 3.9220. Min Range: -3.9220

Max Act: 3.8282. Min Act: -0.1700

Data Index: 1432633 (Python Code)

Max Activating Token Index: 614