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

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

Neuron 318 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: 3.7747. Min Range: -3.7747

Max Act: 3.7747. Min Act: -0.1700

Data Index: 1334704 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.7434. Min Act: -0.1700

Data Index: 236227 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.6809. Min Act: -0.1700

Data Index: 1139791 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.6496. Min Act: -0.1700

Data Index: 779017 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.6183. Min Act: -0.1700

Data Index: 635207 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.5556. Min Act: -0.1700

Data Index: 406604 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.5869. Min Act: -0.1700

Data Index: 800796 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.5869. Min Act: -0.1700

Data Index: 907811 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.5869. Min Act: -0.1700

Data Index: 196787 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.5869. Min Act: -0.1700

Data Index: 88894 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.5556. Min Act: -0.1700

Data Index: 682084 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.5556. Min Act: -0.1700

Data Index: 1052361 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.6183. Min Act: -0.1700

Data Index: 1183932 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.5556. Min Act: -0.1700

Data Index: 36304 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.5556. Min Act: -0.1700

Data Index: 1177454 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.5556. Min Act: -0.1700

Data Index: 304654 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.5556. Min Act: -0.1700

Data Index: 76513 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.5556. Min Act: -0.1700

Data Index: 1096507 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.5556. Min Act: -0.1700

Data Index: 1059155 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.5556. Min Act: -0.1700

Data Index: 247354 (C4 (Web Text))

Max Activating Token Index: 241