Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1831 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9091. Min Range: -9.9091
Max Act: 9.9091. Min Act: -0.1700
Data Index: 7548147 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9091. Min Range: -9.9091
Max Act: 9.7841. Min Act: -0.1700
Data Index: 6215675 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9091. Min Range: -9.9091
Max Act: 9.5341. Min Act: -0.1700
Data Index: 2494501 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9091. Min Range: -9.9091
Max Act: 9.4716. Min Act: -0.1700
Data Index: 1056669 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9091. Min Range: -9.9091
Max Act: 9.4716. Min Act: -0.1700
Data Index: 1174088 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9091. Min Range: -9.9091
Max Act: 9.4716. Min Act: -0.1700
Data Index: 5193802 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9091. Min Range: -9.9091
Max Act: 9.4716. Min Act: -0.1700
Data Index: 3350899 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9091. Min Range: -9.9091
Max Act: 9.4091. Min Act: -0.1700
Data Index: 5125664 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9091. Min Range: -9.9091
Max Act: 9.4091. Min Act: -0.1700
Data Index: 8100512 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9091. Min Range: -9.9091
Max Act: 9.4716. Min Act: -0.1700
Data Index: 7668977 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9091. Min Range: -9.9091
Max Act: 9.4091. Min Act: -0.1700
Data Index: 4355456 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9091. Min Range: -9.9091
Max Act: 9.4091. Min Act: -0.1700
Data Index: 3036315 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9091. Min Range: -9.9091
Max Act: 9.4716. Min Act: -0.1700
Data Index: 7214732 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9091. Min Range: -9.9091
Max Act: 9.4091. Min Act: -0.1700
Data Index: 5729866 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9091. Min Range: -9.9091
Max Act: 9.3466. Min Act: -0.1700
Data Index: 1434947 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9091. Min Range: -9.9091
Max Act: 9.3466. Min Act: -0.1700
Data Index: 6673676 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9091. Min Range: -9.9091
Max Act: 9.3466. Min Act: -0.1700
Data Index: 737185 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9091. Min Range: -9.9091
Max Act: 9.3466. Min Act: -0.1700
Data Index: 804916 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9091. Min Range: -9.9091
Max Act: 9.4091. Min Act: -0.1700
Data Index: 4616410 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9091. Min Range: -9.9091
Max Act: 9.2841. Min Act: -0.1700
Data Index: 2992449 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19