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

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

Neuron 243 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.8033. Min Act: -0.1700

Data Index: 1304846 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.8345. Min Act: -0.1700

Data Index: 256863 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.7720. Min Act: -0.1700

Data Index: 1298134 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.7720. Min Act: -0.1700

Data Index: 45973 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.7094. Min Act: -0.1700

Data Index: 373096 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.6781. Min Act: -0.1700

Data Index: 408843 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.6781. Min Act: -0.1700

Data Index: 1305092 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.6781. Min Act: -0.1700

Data Index: 1135161 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.6781. Min Act: -0.1700

Data Index: 1211668 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.7094. Min Act: -0.1700

Data Index: 588918 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.6781. Min Act: -0.1700

Data Index: 1310903 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.6468. Min Act: -0.1700

Data Index: 1046539 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.6155. Min Act: -0.1700

Data Index: 1328436 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.6155. Min Act: -0.1700

Data Index: 1291727 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.6468. Min Act: -0.1700

Data Index: 175306 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.6155. Min Act: -0.1700

Data Index: 907042 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.6468. Min Act: -0.1700

Data Index: 439325 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.6155. Min Act: -0.1700

Data Index: 57397 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.6468. Min Act: -0.1700

Data Index: 1191802 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.6781. Min Act: -0.1700

Data Index: 731262 (C4 (Web Text))

Max Activating Token Index: 567