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

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

Neuron 367 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: 5.6238. Min Range: -5.6238

Max Act: 5.6238. Min Act: -0.1700

Data Index: 1384237 (Python Code)

Max Activating Token Index: 965

Text #1

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.5613. Min Act: -0.1700

Data Index: 1407720 (Python Code)

Max Activating Token Index: 371

Text #2

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.5613. Min Act: -0.1700

Data Index: 1577683 (Python Code)

Max Activating Token Index: 334

Text #3

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.5613. Min Act: -0.1700

Data Index: 1618717 (Python Code)

Max Activating Token Index: 102

Text #4

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.5300. Min Act: -0.1700

Data Index: 1383150 (Python Code)

Max Activating Token Index: 825

Text #5

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.4988. Min Act: -0.1700

Data Index: 1578064 (Python Code)

Max Activating Token Index: 205

Text #6

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.4675. Min Act: -0.1700

Data Index: 1603847 (Python Code)

Max Activating Token Index: 789

Text #7

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.4988. Min Act: -0.1700

Data Index: 1420373 (Python Code)

Max Activating Token Index: 651

Text #8

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.4363. Min Act: -0.1700

Data Index: 1557138 (Python Code)

Max Activating Token Index: 710

Text #9

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.4363. Min Act: -0.1700

Data Index: 1610250 (Python Code)

Max Activating Token Index: 156

Text #10

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.4050. Min Act: -0.1700

Data Index: 1618265 (Python Code)

Max Activating Token Index: 260

Text #11

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.4363. Min Act: -0.1700

Data Index: 1645807 (Python Code)

Max Activating Token Index: 805

Text #12

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.4363. Min Act: -0.1700

Data Index: 1650142 (Python Code)

Max Activating Token Index: 255

Text #13

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.4363. Min Act: -0.1700

Data Index: 368875 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.4050. Min Act: -0.1700

Data Index: 1462889 (Python Code)

Max Activating Token Index: 309

Text #15

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.4050. Min Act: -0.1700

Data Index: 1614756 (Python Code)

Max Activating Token Index: 678

Text #16

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.4363. Min Act: -0.1700

Data Index: 1530702 (Python Code)

Max Activating Token Index: 422

Text #17

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.4050. Min Act: -0.1700

Data Index: 1530583 (Python Code)

Max Activating Token Index: 54

Text #18

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.4363. Min Act: -0.1700

Data Index: 1408940 (Python Code)

Max Activating Token Index: 279

Text #19

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.4050. Min Act: -0.1700

Data Index: 1636602 (Python Code)

Max Activating Token Index: 116