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

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

Neuron 1108 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: 3.6021. Min Range: -3.6021

Max Act: 3.5864. Min Act: -0.1700

Data Index: 523333 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 3.6021. Min Range: -3.6021

Max Act: 3.5864. Min Act: -0.1700

Data Index: 1134226 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 3.6021. Min Range: -3.6021

Max Act: 3.6021. Min Act: -0.1700

Data Index: 344979 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 3.6021. Min Range: -3.6021

Max Act: 3.5708. Min Act: -0.1700

Data Index: 1353097 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 3.6021. Min Range: -3.6021

Max Act: 3.5238. Min Act: -0.1700

Data Index: 836139 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 3.6021. Min Range: -3.6021

Max Act: 3.4768. Min Act: -0.1700

Data Index: 1127644 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 3.6021. Min Range: -3.6021

Max Act: 3.4454. Min Act: -0.1700

Data Index: 545306 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 3.6021. Min Range: -3.6021

Max Act: 3.4611. Min Act: -0.1700

Data Index: 679455 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 3.6021. Min Range: -3.6021

Max Act: 3.4141. Min Act: -0.1700

Data Index: 1063403 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 3.6021. Min Range: -3.6021

Max Act: 3.4298. Min Act: -0.1700

Data Index: 1121761 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 3.6021. Min Range: -3.6021

Max Act: 3.4298. Min Act: -0.1700

Data Index: 1287915 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 3.6021. Min Range: -3.6021

Max Act: 3.4298. Min Act: -0.1700

Data Index: 1284447 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 3.6021. Min Range: -3.6021

Max Act: 3.4141. Min Act: -0.1700

Data Index: 293540 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 3.6021. Min Range: -3.6021

Max Act: 3.3984. Min Act: -0.1700

Data Index: 591416 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 3.6021. Min Range: -3.6021

Max Act: 3.3984. Min Act: -0.1700

Data Index: 1159634 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 3.6021. Min Range: -3.6021

Max Act: 3.3827. Min Act: -0.1700

Data Index: 894973 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 3.6021. Min Range: -3.6021

Max Act: 3.3670. Min Act: -0.1700

Data Index: 1266096 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 3.6021. Min Range: -3.6021

Max Act: 3.3984. Min Act: -0.1700

Data Index: 600252 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 3.6021. Min Range: -3.6021

Max Act: 3.3984. Min Act: -0.1700

Data Index: 1097291 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 3.6021. Min Range: -3.6021

Max Act: 3.3827. Min Act: -0.1700

Data Index: 337434 (C4 (Web Text))

Max Activating Token Index: 681