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

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

Neuron 768 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.7521. Min Act: -0.1700

Data Index: 1379235 (Python Code)

Max Activating Token Index: 759

Text #1

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.4546. Min Act: -0.1700

Data Index: 1467246 (Python Code)

Max Activating Token Index: 832

Text #2

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.3291. Min Act: -0.1700

Data Index: 1502677 (Python Code)

Max Activating Token Index: 14

Text #3

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.3134. Min Act: -0.1700

Data Index: 1480916 (Python Code)

Max Activating Token Index: 183

Text #4

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.3134. Min Act: -0.1700

Data Index: 1543910 (Python Code)

Max Activating Token Index: 164

Text #5

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.2977. Min Act: -0.1700

Data Index: 1526155 (Python Code)

Max Activating Token Index: 542

Text #6

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.2820. Min Act: -0.1700

Data Index: 1611528 (Python Code)

Max Activating Token Index: 995

Text #7

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.2820. Min Act: -0.1700

Data Index: 1607288 (Python Code)

Max Activating Token Index: 444

Text #8

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.2663. Min Act: -0.1700

Data Index: 839013 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.2663. Min Act: -0.1700

Data Index: 1476265 (Python Code)

Max Activating Token Index: 1003

Text #10

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.2663. Min Act: -0.1700

Data Index: 1471477 (Python Code)

Max Activating Token Index: 401

Text #11

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.2349. Min Act: -0.1700

Data Index: 1549391 (Python Code)

Max Activating Token Index: 869

Text #12

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.2349. Min Act: -0.1700

Data Index: 1438343 (Python Code)

Max Activating Token Index: 779

Text #13

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.2191. Min Act: -0.1700

Data Index: 1436649 (Python Code)

Max Activating Token Index: 145

Text #14

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.2034. Min Act: -0.1700

Data Index: 1450453 (Python Code)

Max Activating Token Index: 830

Text #15

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.2191. Min Act: -0.1700

Data Index: 1642540 (Python Code)

Max Activating Token Index: 877

Text #16

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.1877. Min Act: -0.1700

Data Index: 1466229 (Python Code)

Max Activating Token Index: 950

Text #17

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.2191. Min Act: -0.1700

Data Index: 1651228 (Python Code)

Max Activating Token Index: 375

Text #18

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.2034. Min Act: -0.1700

Data Index: 1420694 (Python Code)

Max Activating Token Index: 333

Text #19

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.1877. Min Act: -0.1700

Data Index: 1618861 (Python Code)

Max Activating Token Index: 197