Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4904 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7385. Min Range: -6.7385
Max Act: 6.7385. Min Act: -0.1700
Data Index: 5641254 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7385. Min Range: -6.7385
Max Act: 6.6135. Min Act: -0.1700
Data Index: 2469993 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7385. Min Range: -6.7385
Max Act: 6.5510. Min Act: -0.1700
Data Index: 4777630 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7385. Min Range: -6.7385
Max Act: 6.3322. Min Act: -0.1700
Data Index: 7127111 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7385. Min Range: -6.7385
Max Act: 6.2385. Min Act: -0.1700
Data Index: 6503962 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7385. Min Range: -6.7385
Max Act: 6.2385. Min Act: -0.1700
Data Index: 7343367 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7385. Min Range: -6.7385
Max Act: 6.2385. Min Act: -0.1700
Data Index: 3319723 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7385. Min Range: -6.7385
Max Act: 6.2072. Min Act: -0.1700
Data Index: 4487815 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7385. Min Range: -6.7385
Max Act: 6.2072. Min Act: -0.1700
Data Index: 5695707 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7385. Min Range: -6.7385
Max Act: 6.2072. Min Act: -0.1700
Data Index: 5622735 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7385. Min Range: -6.7385
Max Act: 6.1760. Min Act: -0.1700
Data Index: 489776 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7385. Min Range: -6.7385
Max Act: 6.1447. Min Act: -0.1700
Data Index: 1266132 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7385. Min Range: -6.7385
Max Act: 6.1447. Min Act: -0.1700
Data Index: 6091483 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7385. Min Range: -6.7385
Max Act: 6.1135. Min Act: -0.1700
Data Index: 645936 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7385. Min Range: -6.7385
Max Act: 6.0822. Min Act: -0.1700
Data Index: 1990798 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7385. Min Range: -6.7385
Max Act: 6.0822. Min Act: -0.1700
Data Index: 1328134 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7385. Min Range: -6.7385
Max Act: 6.0822. Min Act: -0.1700
Data Index: 687345 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7385. Min Range: -6.7385
Max Act: 6.0822. Min Act: -0.1700
Data Index: 5309064 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7385. Min Range: -6.7385
Max Act: 6.0510. Min Act: -0.1700
Data Index: 2380597 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7385. Min Range: -6.7385
Max Act: 6.0510. Min Act: -0.1700
Data Index: 5068111 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19