Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2989 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1661. Min Range: -6.1661
Max Act: 6.1661. Min Act: -0.1700
Data Index: 5373156 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1661. Min Range: -6.1661
Max Act: 6.1036. Min Act: -0.1700
Data Index: 6389856 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1661. Min Range: -6.1661
Max Act: 5.9161. Min Act: -0.1700
Data Index: 4356550 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1661. Min Range: -6.1661
Max Act: 5.8536. Min Act: -0.1700
Data Index: 6049008 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1661. Min Range: -6.1661
Max Act: 5.8848. Min Act: -0.1700
Data Index: 6249046 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1661. Min Range: -6.1661
Max Act: 5.8223. Min Act: -0.1700
Data Index: 1778444 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1661. Min Range: -6.1661
Max Act: 5.7911. Min Act: -0.1700
Data Index: 2642994 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1661. Min Range: -6.1661
Max Act: 5.7598. Min Act: -0.1700
Data Index: 280365 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1661. Min Range: -6.1661
Max Act: 5.6348. Min Act: -0.1700
Data Index: 449839 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1661. Min Range: -6.1661
Max Act: 5.6036. Min Act: -0.1700
Data Index: 1031383 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1661. Min Range: -6.1661
Max Act: 5.6348. Min Act: -0.1700
Data Index: 6676908 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1661. Min Range: -6.1661
Max Act: 5.6036. Min Act: -0.1700
Data Index: 6261550 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1661. Min Range: -6.1661
Max Act: 5.5723. Min Act: -0.1700
Data Index: 3237425 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1661. Min Range: -6.1661
Max Act: 5.5723. Min Act: -0.1700
Data Index: 1434980 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1661. Min Range: -6.1661
Max Act: 5.5723. Min Act: -0.1700
Data Index: 7551446 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1661. Min Range: -6.1661
Max Act: 5.5723. Min Act: -0.1700
Data Index: 5729888 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1661. Min Range: -6.1661
Max Act: 5.5411. Min Act: -0.1700
Data Index: 1021126 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1661. Min Range: -6.1661
Max Act: 5.5411. Min Act: -0.1700
Data Index: 1043921 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1661. Min Range: -6.1661
Max Act: 5.5411. Min Act: -0.1700
Data Index: 3652125 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1661. Min Range: -6.1661
Max Act: 5.5411. Min Act: -0.1700
Data Index: 6543347 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19