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

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

Neuron 1552 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8524. Min Range: -3.8524

Max Act: 3.8524. Min Act: -0.1700

Data Index: 1010416 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 3.8524. Min Range: -3.8524

Max Act: 3.8211. Min Act: -0.1700

Data Index: 218039 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 3.8524. Min Range: -3.8524

Max Act: 3.7898. Min Act: -0.1700

Data Index: 729809 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 3.8524. Min Range: -3.8524

Max Act: 3.7585. Min Act: -0.1700

Data Index: 763730 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 3.8524. Min Range: -3.8524

Max Act: 3.7898. Min Act: -0.1700

Data Index: 745961 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 3.8524. Min Range: -3.8524

Max Act: 3.7898. Min Act: -0.1700

Data Index: 792953 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.8524. Min Range: -3.8524

Max Act: 3.6959. Min Act: -0.1700

Data Index: 836371 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 3.8524. Min Range: -3.8524

Max Act: 3.7272. Min Act: -0.1700

Data Index: 1347968 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 3.8524. Min Range: -3.8524

Max Act: 3.7585. Min Act: -0.1700

Data Index: 645789 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 3.8524. Min Range: -3.8524

Max Act: 3.7585. Min Act: -0.1700

Data Index: 1266396 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 3.8524. Min Range: -3.8524

Max Act: 3.7272. Min Act: -0.1700

Data Index: 21071 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 3.8524. Min Range: -3.8524

Max Act: 3.6646. Min Act: -0.1700

Data Index: 520562 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 3.8524. Min Range: -3.8524

Max Act: 3.6646. Min Act: -0.1700

Data Index: 885090 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 3.8524. Min Range: -3.8524

Max Act: 3.6333. Min Act: -0.1700

Data Index: 941077 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 3.8524. Min Range: -3.8524

Max Act: 3.6646. Min Act: -0.1700

Data Index: 856502 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 3.8524. Min Range: -3.8524

Max Act: 3.6959. Min Act: -0.1700

Data Index: 770095 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 3.8524. Min Range: -3.8524

Max Act: 3.6646. Min Act: -0.1700

Data Index: 800002 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 3.8524. Min Range: -3.8524

Max Act: 3.6333. Min Act: -0.1700

Data Index: 1099162 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 3.8524. Min Range: -3.8524

Max Act: 3.6333. Min Act: -0.1700

Data Index: 830266 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 3.8524. Min Range: -3.8524

Max Act: 3.6333. Min Act: -0.1700

Data Index: 1170134 (C4 (Web Text))

Max Activating Token Index: 375