Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 152 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.2478. Min Range: -5.2478

Max Act: 5.2478. Min Act: -0.1700

Data Index: 1347543 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.2478. Min Range: -5.2478

Max Act: 5.1540. Min Act: -0.1700

Data Index: 381069 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 5.2478. Min Range: -5.2478

Max Act: 4.9665. Min Act: -0.1700

Data Index: 169202 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 5.2478. Min Range: -5.2478

Max Act: 4.7634. Min Act: -0.1700

Data Index: 239018 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 5.2478. Min Range: -5.2478

Max Act: 4.7478. Min Act: -0.1700

Data Index: 334994 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 5.2478. Min Range: -5.2478

Max Act: 4.6853. Min Act: -0.1700

Data Index: 1357738 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 5.2478. Min Range: -5.2478

Max Act: 4.6696. Min Act: -0.1700

Data Index: 1294342 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 5.2478. Min Range: -5.2478

Max Act: 4.6540. Min Act: -0.1700

Data Index: 371601 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 5.2478. Min Range: -5.2478

Max Act: 4.6540. Min Act: -0.1700

Data Index: 1313505 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 5.2478. Min Range: -5.2478

Max Act: 4.6384. Min Act: -0.1700

Data Index: 269705 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 5.2478. Min Range: -5.2478

Max Act: 4.6384. Min Act: -0.1700

Data Index: 1294298 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 5.2478. Min Range: -5.2478

Max Act: 4.6540. Min Act: -0.1700

Data Index: 1138350 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 5.2478. Min Range: -5.2478

Max Act: 4.5915. Min Act: -0.1700

Data Index: 39184 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 5.2478. Min Range: -5.2478

Max Act: 4.5759. Min Act: -0.1700

Data Index: 465740 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 5.2478. Min Range: -5.2478

Max Act: 4.5446. Min Act: -0.1700

Data Index: 1086011 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 5.2478. Min Range: -5.2478

Max Act: 4.5603. Min Act: -0.1700

Data Index: 951870 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 5.2478. Min Range: -5.2478

Max Act: 4.5446. Min Act: -0.1700

Data Index: 1216117 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 5.2478. Min Range: -5.2478

Max Act: 4.5290. Min Act: -0.1700

Data Index: 560504 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 5.2478. Min Range: -5.2478

Max Act: 4.4977. Min Act: -0.1700

Data Index: 862711 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 5.2478. Min Range: -5.2478

Max Act: 4.4821. Min Act: -0.1700

Data Index: 198416 (C4 (Web Text))

Max Activating Token Index: 838