Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1517 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8152. Min Range: -6.8152
Max Act: 6.8152. Min Act: -0.1700
Data Index: 4811394 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8152. Min Range: -6.8152
Max Act: 6.8152. Min Act: -0.1700
Data Index: 723365 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8152. Min Range: -6.8152
Max Act: 6.8152. Min Act: -0.1700
Data Index: 3983496 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8152. Min Range: -6.8152
Max Act: 6.7215. Min Act: -0.1700
Data Index: 6035366 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8152. Min Range: -6.8152
Max Act: 6.7215. Min Act: -0.1700
Data Index: 1340423 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8152. Min Range: -6.8152
Max Act: 6.6590. Min Act: -0.1700
Data Index: 8514524 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8152. Min Range: -6.8152
Max Act: 6.6277. Min Act: -0.1700
Data Index: 1556011 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8152. Min Range: -6.8152
Max Act: 6.5652. Min Act: -0.1700
Data Index: 2845116 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8152. Min Range: -6.8152
Max Act: 6.5340. Min Act: -0.1700
Data Index: 5732131 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8152. Min Range: -6.8152
Max Act: 6.5027. Min Act: -0.1700
Data Index: 5849821 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8152. Min Range: -6.8152
Max Act: 6.5340. Min Act: -0.1700
Data Index: 7263782 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8152. Min Range: -6.8152
Max Act: 6.4715. Min Act: -0.1700
Data Index: 349957 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8152. Min Range: -6.8152
Max Act: 6.4715. Min Act: -0.1700
Data Index: 7807365 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8152. Min Range: -6.8152
Max Act: 6.5027. Min Act: -0.1700
Data Index: 8169384 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8152. Min Range: -6.8152
Max Act: 6.4402. Min Act: -0.1700
Data Index: 376815 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8152. Min Range: -6.8152
Max Act: 6.4402. Min Act: -0.1700
Data Index: 3718471 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8152. Min Range: -6.8152
Max Act: 6.4090. Min Act: -0.1700
Data Index: 4584145 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8152. Min Range: -6.8152
Max Act: 6.4090. Min Act: -0.1700
Data Index: 3544973 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8152. Min Range: -6.8152
Max Act: 6.4090. Min Act: -0.1700
Data Index: 2213117 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8152. Min Range: -6.8152
Max Act: 6.3465. Min Act: -0.1700
Data Index: 4380679 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19