Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4100 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0666. Min Range: -4.0666
Max Act: 4.0666. Min Act: -0.1700
Data Index: 1108253 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0666. Min Range: -4.0666
Max Act: 4.0040. Min Act: -0.1700
Data Index: 7295419 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0666. Min Range: -4.0666
Max Act: 4.0040. Min Act: -0.1700
Data Index: 6899774 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0666. Min Range: -4.0666
Max Act: 3.9728. Min Act: -0.1700
Data Index: 227588 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0666. Min Range: -4.0666
Max Act: 3.9728. Min Act: -0.1700
Data Index: 1812628 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0666. Min Range: -4.0666
Max Act: 3.9415. Min Act: -0.1700
Data Index: 6253902 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0666. Min Range: -4.0666
Max Act: 3.9415. Min Act: -0.1700
Data Index: 3943290 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0666. Min Range: -4.0666
Max Act: 3.9103. Min Act: -0.1700
Data Index: 2721337 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0666. Min Range: -4.0666
Max Act: 3.8790. Min Act: -0.1700
Data Index: 6046901 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0666. Min Range: -4.0666
Max Act: 3.8790. Min Act: -0.1700
Data Index: 2440952 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0666. Min Range: -4.0666
Max Act: 3.8790. Min Act: -0.1700
Data Index: 6355856 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0666. Min Range: -4.0666
Max Act: 3.8790. Min Act: -0.1700
Data Index: 6795387 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0666. Min Range: -4.0666
Max Act: 3.8790. Min Act: -0.1700
Data Index: 572211 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0666. Min Range: -4.0666
Max Act: 3.8477. Min Act: -0.1700
Data Index: 5027045 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0666. Min Range: -4.0666
Max Act: 3.8477. Min Act: -0.1700
Data Index: 8385215 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0666. Min Range: -4.0666
Max Act: 3.8165. Min Act: -0.1700
Data Index: 6678335 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0666. Min Range: -4.0666
Max Act: 3.8165. Min Act: -0.1700
Data Index: 1478103 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0666. Min Range: -4.0666
Max Act: 3.8165. Min Act: -0.1700
Data Index: 36789 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0666. Min Range: -4.0666
Max Act: 3.8165. Min Act: -0.1700
Data Index: 5934079 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0666. Min Range: -4.0666
Max Act: 3.8165. Min Act: -0.1700
Data Index: 279559 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19