Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4052 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0719. Min Range: -4.0719
Max Act: 4.0719. Min Act: -0.1700
Data Index: 8763483 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0719. Min Range: -4.0719
Max Act: 4.0719. Min Act: -0.1700
Data Index: 8743592 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0719. Min Range: -4.0719
Max Act: 4.0094. Min Act: -0.1700
Data Index: 6659495 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0719. Min Range: -4.0719
Max Act: 4.0094. Min Act: -0.1700
Data Index: 3800648 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0719. Min Range: -4.0719
Max Act: 3.9781. Min Act: -0.1700
Data Index: 8233783 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0719. Min Range: -4.0719
Max Act: 3.9781. Min Act: -0.1700
Data Index: 191485 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0719. Min Range: -4.0719
Max Act: 3.9781. Min Act: -0.1700
Data Index: 1798235 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0719. Min Range: -4.0719
Max Act: 3.9781. Min Act: -0.1700
Data Index: 4438748 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0719. Min Range: -4.0719
Max Act: 3.9781. Min Act: -0.1700
Data Index: 3781291 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0719. Min Range: -4.0719
Max Act: 3.9468. Min Act: -0.1700
Data Index: 3895761 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0719. Min Range: -4.0719
Max Act: 3.9468. Min Act: -0.1700
Data Index: 1784681 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0719. Min Range: -4.0719
Max Act: 3.9468. Min Act: -0.1700
Data Index: 8416479 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0719. Min Range: -4.0719
Max Act: 3.9468. Min Act: -0.1700
Data Index: 2154916 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0719. Min Range: -4.0719
Max Act: 3.9156. Min Act: -0.1700
Data Index: 345355 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0719. Min Range: -4.0719
Max Act: 3.9781. Min Act: -0.1700
Data Index: 6437189 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0719. Min Range: -4.0719
Max Act: 3.9468. Min Act: -0.1700
Data Index: 4793631 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0719. Min Range: -4.0719
Max Act: 3.9156. Min Act: -0.1700
Data Index: 3131246 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0719. Min Range: -4.0719
Max Act: 3.8843. Min Act: -0.1700
Data Index: 5704659 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0719. Min Range: -4.0719
Max Act: 3.9156. Min Act: -0.1700
Data Index: 6007245 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0719. Min Range: -4.0719
Max Act: 3.9156. Min Act: -0.1700
Data Index: 1832050 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19