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

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

Neuron 123 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: 5.2158. Min Range: -5.2158

Max Act: 5.2158. Min Act: -0.1700

Data Index: 1120504 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 5.2158. Min Range: -5.2158

Max Act: 5.1220. Min Act: -0.1700

Data Index: 1335784 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 5.2158. Min Range: -5.2158

Max Act: 5.0908. Min Act: -0.1700

Data Index: 624123 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 5.2158. Min Range: -5.2158

Max Act: 4.9658. Min Act: -0.1700

Data Index: 927184 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 5.2158. Min Range: -5.2158

Max Act: 4.9814. Min Act: -0.1700

Data Index: 945855 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 5.2158. Min Range: -5.2158

Max Act: 4.9189. Min Act: -0.1700

Data Index: 611937 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 5.2158. Min Range: -5.2158

Max Act: 4.9501. Min Act: -0.1700

Data Index: 145601 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 5.2158. Min Range: -5.2158

Max Act: 4.9189. Min Act: -0.1700

Data Index: 872389 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 5.2158. Min Range: -5.2158

Max Act: 4.9189. Min Act: -0.1700

Data Index: 979879 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 5.2158. Min Range: -5.2158

Max Act: 4.8876. Min Act: -0.1700

Data Index: 1270846 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 5.2158. Min Range: -5.2158

Max Act: 4.8876. Min Act: -0.1700

Data Index: 1005964 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 5.2158. Min Range: -5.2158

Max Act: 4.8720. Min Act: -0.1700

Data Index: 916474 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 5.2158. Min Range: -5.2158

Max Act: 4.9033. Min Act: -0.1700

Data Index: 1201558 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 5.2158. Min Range: -5.2158

Max Act: 4.8720. Min Act: -0.1700

Data Index: 155690 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 5.2158. Min Range: -5.2158

Max Act: 4.9033. Min Act: -0.1700

Data Index: 3458 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 5.2158. Min Range: -5.2158

Max Act: 4.8251. Min Act: -0.1700

Data Index: 1290221 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 5.2158. Min Range: -5.2158

Max Act: 4.9033. Min Act: -0.1700

Data Index: 135016 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 5.2158. Min Range: -5.2158

Max Act: 4.7939. Min Act: -0.1700

Data Index: 951232 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 5.2158. Min Range: -5.2158

Max Act: 4.8095. Min Act: -0.1700

Data Index: 446921 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 5.2158. Min Range: -5.2158

Max Act: 4.8251. Min Act: -0.1700

Data Index: 1284412 (C4 (Web Text))

Max Activating Token Index: 21