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

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

Neuron 617 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1090. Min Range: -5.1090

Max Act: 5.1090. Min Act: -0.1700

Data Index: 801380 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 5.1090. Min Range: -5.1090

Max Act: 5.0778. Min Act: -0.1700

Data Index: 1157179 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 5.1090. Min Range: -5.1090

Max Act: 5.0778. Min Act: -0.1700

Data Index: 763195 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 5.1090. Min Range: -5.1090

Max Act: 5.1090. Min Act: -0.1700

Data Index: 632355 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 5.1090. Min Range: -5.1090

Max Act: 5.1090. Min Act: -0.1700

Data Index: 429089 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 5.1090. Min Range: -5.1090

Max Act: 5.0778. Min Act: -0.1700

Data Index: 1064531 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 5.1090. Min Range: -5.1090

Max Act: 5.0778. Min Act: -0.1700

Data Index: 181807 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 5.1090. Min Range: -5.1090

Max Act: 5.0465. Min Act: -0.1700

Data Index: 206777 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 5.1090. Min Range: -5.1090

Max Act: 5.0153. Min Act: -0.1700

Data Index: 222444 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 5.1090. Min Range: -5.1090

Max Act: 5.0153. Min Act: -0.1700

Data Index: 423996 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 5.1090. Min Range: -5.1090

Max Act: 5.0778. Min Act: -0.1700

Data Index: 1129372 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 5.1090. Min Range: -5.1090

Max Act: 5.0465. Min Act: -0.1700

Data Index: 1147227 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 5.1090. Min Range: -5.1090

Max Act: 5.0465. Min Act: -0.1700

Data Index: 555401 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 5.1090. Min Range: -5.1090

Max Act: 5.0465. Min Act: -0.1700

Data Index: 505741 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 5.1090. Min Range: -5.1090

Max Act: 5.0465. Min Act: -0.1700

Data Index: 463861 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 5.1090. Min Range: -5.1090

Max Act: 4.9840. Min Act: -0.1700

Data Index: 28950 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 5.1090. Min Range: -5.1090

Max Act: 5.0465. Min Act: -0.1700

Data Index: 396996 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 5.1090. Min Range: -5.1090

Max Act: 4.9840. Min Act: -0.1700

Data Index: 115198 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 5.1090. Min Range: -5.1090

Max Act: 4.9840. Min Act: -0.1700

Data Index: 231319 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 5.1090. Min Range: -5.1090

Max Act: 5.0153. Min Act: -0.1700

Data Index: 748736 (C4 (Web Text))

Max Activating Token Index: 91