Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1072 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.7412. Min Act: -0.1700

Data Index: 1188661 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.7031. Min Act: -0.1700

Data Index: 1170235 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.4753. Min Act: -0.1700

Data Index: 341476 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.4971. Min Act: -0.1700

Data Index: 193851 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.4898. Min Act: -0.1700

Data Index: 1283984 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.4917. Min Act: -0.1700

Data Index: 309355 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.4907. Min Act: -0.1700

Data Index: 967062 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.4783. Min Act: -0.1700

Data Index: 715381 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.4884. Min Act: -0.1700

Data Index: 189383 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.4434. Min Act: -0.1700

Data Index: 944099 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.4669. Min Act: -0.1700

Data Index: 890898 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.4517. Min Act: -0.1700

Data Index: 806248 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.4769. Min Act: -0.1700

Data Index: 644362 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.4560. Min Act: -0.1700

Data Index: 1273801 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.4453. Min Act: -0.1700

Data Index: 645169 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.4500. Min Act: -0.1700

Data Index: 669239 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.4609. Min Act: -0.1700

Data Index: 336049 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.4206. Min Act: -0.1700

Data Index: 200641 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.4144. Min Act: -0.1700

Data Index: 371516 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.4065. Min Act: -0.1700

Data Index: 1175358 (C4 (Web Text))

Max Activating Token Index: 839