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

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

Neuron 422 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: 5.2918. Min Range: -5.2918

Max Act: 5.2918. Min Act: -0.1700

Data Index: 580825 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 5.2918. Min Range: -5.2918

Max Act: 5.1877. Min Act: -0.1700

Data Index: 1379383 (Python Code)

Max Activating Token Index: 791

Text #2

Max Range: 5.2918. Min Range: -5.2918

Max Act: 5.1793. Min Act: -0.1700

Data Index: 529235 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 5.2918. Min Range: -5.2918

Max Act: 5.1619. Min Act: -0.1700

Data Index: 900674 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 5.2918. Min Range: -5.2918

Max Act: 5.1422. Min Act: -0.1700

Data Index: 1223774 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 5.2918. Min Range: -5.2918

Max Act: 5.1422. Min Act: -0.1700

Data Index: 428115 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 5.2918. Min Range: -5.2918

Max Act: 5.1284. Min Act: -0.1700

Data Index: 1504041 (Python Code)

Max Activating Token Index: 677

Text #7

Max Range: 5.2918. Min Range: -5.2918

Max Act: 5.1215. Min Act: -0.1700

Data Index: 1639324 (Python Code)

Max Activating Token Index: 742

Text #8

Max Range: 5.2918. Min Range: -5.2918

Max Act: 5.1241. Min Act: -0.1700

Data Index: 1456107 (Python Code)

Max Activating Token Index: 748

Text #9

Max Range: 5.2918. Min Range: -5.2918

Max Act: 5.1142. Min Act: -0.1700

Data Index: 1537969 (Python Code)

Max Activating Token Index: 276

Text #10

Max Range: 5.2918. Min Range: -5.2918

Max Act: 5.1277. Min Act: -0.1700

Data Index: 1579346 (Python Code)

Max Activating Token Index: 885

Text #11

Max Range: 5.2918. Min Range: -5.2918

Max Act: 5.1238. Min Act: -0.1700

Data Index: 552893 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 5.2918. Min Range: -5.2918

Max Act: 5.1336. Min Act: -0.1700

Data Index: 560399 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 5.2918. Min Range: -5.2918

Max Act: 5.0895. Min Act: -0.1700

Data Index: 1363464 (Python Code)

Max Activating Token Index: 728

Text #14

Max Range: 5.2918. Min Range: -5.2918

Max Act: 5.0869. Min Act: -0.1700

Data Index: 1647107 (Python Code)

Max Activating Token Index: 380

Text #15

Max Range: 5.2918. Min Range: -5.2918

Max Act: 5.0825. Min Act: -0.1700

Data Index: 271580 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 5.2918. Min Range: -5.2918

Max Act: 5.0746. Min Act: -0.1700

Data Index: 1626612 (Python Code)

Max Activating Token Index: 174

Text #17

Max Range: 5.2918. Min Range: -5.2918

Max Act: 5.0536. Min Act: -0.1700

Data Index: 1591175 (Python Code)

Max Activating Token Index: 506

Text #18

Max Range: 5.2918. Min Range: -5.2918

Max Act: 5.0534. Min Act: -0.1700

Data Index: 599927 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 5.2918. Min Range: -5.2918

Max Act: 5.0765. Min Act: -0.1700

Data Index: 660463 (C4 (Web Text))

Max Activating Token Index: 1003