Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3487 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2013. Min Range: -3.2013
Max Act: 3.2013. Min Act: -0.1697
Data Index: 6989795 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2013. Min Range: -3.2013
Max Act: 3.1384. Min Act: -0.1699
Data Index: 3379312 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2013. Min Range: -3.2013
Max Act: 3.1226. Min Act: -0.1700
Data Index: 861755 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2013. Min Range: -3.2013
Max Act: 3.0753. Min Act: -0.1700
Data Index: 4191948 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2013. Min Range: -3.2013
Max Act: 2.9331. Min Act: -0.1700
Data Index: 5898711 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2013. Min Range: -3.2013
Max Act: 2.8855. Min Act: -0.1700
Data Index: 8352636 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2013. Min Range: -3.2013
Max Act: 2.8220. Min Act: -0.1700
Data Index: 7309640 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2013. Min Range: -3.2013
Max Act: 2.8061. Min Act: -0.1700
Data Index: 545491 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2013. Min Range: -3.2013
Max Act: 2.8061. Min Act: -0.1700
Data Index: 7595776 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2013. Min Range: -3.2013
Max Act: 2.8061. Min Act: -0.1696
Data Index: 5148068 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2013. Min Range: -3.2013
Max Act: 2.7901. Min Act: -0.1700
Data Index: 767619 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2013. Min Range: -3.2013
Max Act: 2.7742. Min Act: -0.1696
Data Index: 4953414 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2013. Min Range: -3.2013
Max Act: 2.7583. Min Act: -0.1700
Data Index: 6230302 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2013. Min Range: -3.2013
Max Act: 2.7742. Min Act: -0.1700
Data Index: 1916881 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2013. Min Range: -3.2013
Max Act: 2.7423. Min Act: -0.1700
Data Index: 5371084 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2013. Min Range: -3.2013
Max Act: 2.7583. Min Act: -0.1700
Data Index: 3979108 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2013. Min Range: -3.2013
Max Act: 2.7583. Min Act: -0.1700
Data Index: 1845140 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2013. Min Range: -3.2013
Max Act: 2.7583. Min Act: -0.1700
Data Index: 8051505 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2013. Min Range: -3.2013
Max Act: 2.7583. Min Act: -0.1700
Data Index: 1551153 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2013. Min Range: -3.2013
Max Act: 2.7263. Min Act: -0.1700
Data Index: 2328272 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19