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

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

Neuron 1632 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2439. Min Range: -3.2439

Max Act: 3.2439. Min Act: -0.1700

Data Index: 1225937 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 3.2439. Min Range: -3.2439

Max Act: 3.1495. Min Act: -0.1700

Data Index: 11244 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 3.2439. Min Range: -3.2439

Max Act: 3.1338. Min Act: -0.1700

Data Index: 203971 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 3.2439. Min Range: -3.2439

Max Act: 3.1495. Min Act: -0.1700

Data Index: 899195 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 3.2439. Min Range: -3.2439

Max Act: 3.1180. Min Act: -0.1700

Data Index: 447609 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 3.2439. Min Range: -3.2439

Max Act: 3.0865. Min Act: -0.1700

Data Index: 817890 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 3.2439. Min Range: -3.2439

Max Act: 3.0707. Min Act: -0.1700

Data Index: 356584 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 3.2439. Min Range: -3.2439

Max Act: 3.0707. Min Act: -0.1700

Data Index: 655166 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 3.2439. Min Range: -3.2439

Max Act: 3.0707. Min Act: -0.1700

Data Index: 107962 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 3.2439. Min Range: -3.2439

Max Act: 3.0549. Min Act: -0.1700

Data Index: 927043 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 3.2439. Min Range: -3.2439

Max Act: 3.0391. Min Act: -0.1700

Data Index: 665714 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 3.2439. Min Range: -3.2439

Max Act: 3.0549. Min Act: -0.1700

Data Index: 313364 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 3.2439. Min Range: -3.2439

Max Act: 3.0549. Min Act: -0.1700

Data Index: 115796 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 3.2439. Min Range: -3.2439

Max Act: 3.0391. Min Act: -0.1700

Data Index: 386093 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 3.2439. Min Range: -3.2439

Max Act: 3.0391. Min Act: -0.1700

Data Index: 384716 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 3.2439. Min Range: -3.2439

Max Act: 3.0391. Min Act: -0.1700

Data Index: 283248 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 3.2439. Min Range: -3.2439

Max Act: 3.0391. Min Act: -0.1700

Data Index: 683302 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 3.2439. Min Range: -3.2439

Max Act: 3.0233. Min Act: -0.1700

Data Index: 28358 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 3.2439. Min Range: -3.2439

Max Act: 3.0391. Min Act: -0.1700

Data Index: 908927 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 3.2439. Min Range: -3.2439

Max Act: 3.0075. Min Act: -0.1700

Data Index: 837877 (C4 (Web Text))

Max Activating Token Index: 19