Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5334 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3232. Min Range: -4.3232
Max Act: 4.3232. Min Act: -0.1700
Data Index: 766851 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3232. Min Range: -4.3232
Max Act: 4.3232. Min Act: -0.1700
Data Index: 6024907 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3232. Min Range: -4.3232
Max Act: 4.2919. Min Act: -0.1700
Data Index: 4661560 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3232. Min Range: -4.3232
Max Act: 4.2919. Min Act: -0.1700
Data Index: 1418094 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3232. Min Range: -4.3232
Max Act: 4.2606. Min Act: -0.1700
Data Index: 4735573 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3232. Min Range: -4.3232
Max Act: 4.2606. Min Act: -0.1700
Data Index: 2693812 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3232. Min Range: -4.3232
Max Act: 4.2606. Min Act: -0.1700
Data Index: 7000148 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3232. Min Range: -4.3232
Max Act: 4.1981. Min Act: -0.1700
Data Index: 1003023 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3232. Min Range: -4.3232
Max Act: 4.1981. Min Act: -0.1700
Data Index: 6698137 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3232. Min Range: -4.3232
Max Act: 4.1669. Min Act: -0.1700
Data Index: 8416014 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3232. Min Range: -4.3232
Max Act: 4.1669. Min Act: -0.1700
Data Index: 1701063 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3232. Min Range: -4.3232
Max Act: 4.1981. Min Act: -0.1700
Data Index: 6198345 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3232. Min Range: -4.3232
Max Act: 4.1981. Min Act: -0.1700
Data Index: 6262804 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3232. Min Range: -4.3232
Max Act: 4.1669. Min Act: -0.1700
Data Index: 1421296 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3232. Min Range: -4.3232
Max Act: 4.1044. Min Act: -0.1700
Data Index: 1723997 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3232. Min Range: -4.3232
Max Act: 4.0731. Min Act: -0.1700
Data Index: 4349672 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3232. Min Range: -4.3232
Max Act: 4.1044. Min Act: -0.1700
Data Index: 3509638 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3232. Min Range: -4.3232
Max Act: 4.1044. Min Act: -0.1700
Data Index: 1904005 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3232. Min Range: -4.3232
Max Act: 4.1044. Min Act: -0.1700
Data Index: 7479617 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3232. Min Range: -4.3232
Max Act: 4.1044. Min Act: -0.1700
Data Index: 7767951 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19