Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4292 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5137. Min Range: -6.5137
Max Act: 6.5137. Min Act: -0.1700
Data Index: 2011877 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5137. Min Range: -6.5137
Max Act: 6.5137. Min Act: -0.1700
Data Index: 2997777 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5137. Min Range: -6.5137
Max Act: 6.4512. Min Act: -0.1700
Data Index: 6725970 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5137. Min Range: -6.5137
Max Act: 6.4512. Min Act: -0.1700
Data Index: 6977042 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5137. Min Range: -6.5137
Max Act: 6.4512. Min Act: -0.1700
Data Index: 2200791 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5137. Min Range: -6.5137
Max Act: 6.3887. Min Act: -0.1700
Data Index: 4820629 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5137. Min Range: -6.5137
Max Act: 6.3887. Min Act: -0.1700
Data Index: 8010319 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5137. Min Range: -6.5137
Max Act: 6.3887. Min Act: -0.1700
Data Index: 2672604 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5137. Min Range: -6.5137
Max Act: 6.3887. Min Act: -0.1700
Data Index: 8010318 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5137. Min Range: -6.5137
Max Act: 6.3887. Min Act: -0.1700
Data Index: 3303366 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5137. Min Range: -6.5137
Max Act: 6.3887. Min Act: -0.1700
Data Index: 1015271 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5137. Min Range: -6.5137
Max Act: 6.3574. Min Act: -0.1700
Data Index: 1201249 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5137. Min Range: -6.5137
Max Act: 6.3262. Min Act: -0.1700
Data Index: 426622 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5137. Min Range: -6.5137
Max Act: 6.3262. Min Act: -0.1700
Data Index: 7557086 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5137. Min Range: -6.5137
Max Act: 6.3262. Min Act: -0.1699
Data Index: 3593982 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5137. Min Range: -6.5137
Max Act: 6.2949. Min Act: -0.1700
Data Index: 6850496 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5137. Min Range: -6.5137
Max Act: 6.2949. Min Act: -0.1700
Data Index: 4147093 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5137. Min Range: -6.5137
Max Act: 6.2637. Min Act: -0.1700
Data Index: 5083996 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5137. Min Range: -6.5137
Max Act: 6.2637. Min Act: -0.1700
Data Index: 3137302 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5137. Min Range: -6.5137
Max Act: 6.2637. Min Act: -0.1700
Data Index: 5496369 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19