Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1556 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7949. Min Range: -5.7949
Max Act: 5.7949. Min Act: -0.1700
Data Index: 4310096 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7949. Min Range: -5.7949
Max Act: 5.7637. Min Act: -0.1700
Data Index: 8311803 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7949. Min Range: -5.7949
Max Act: 5.7324. Min Act: -0.1700
Data Index: 7604789 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7949. Min Range: -5.7949
Max Act: 5.7637. Min Act: -0.1700
Data Index: 2660767 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7949. Min Range: -5.7949
Max Act: 5.7324. Min Act: -0.1700
Data Index: 3949208 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7949. Min Range: -5.7949
Max Act: 5.7324. Min Act: -0.1700
Data Index: 5958891 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7949. Min Range: -5.7949
Max Act: 5.7324. Min Act: -0.1700
Data Index: 4469116 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7949. Min Range: -5.7949
Max Act: 5.6387. Min Act: -0.1699
Data Index: 6750768 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7949. Min Range: -5.7949
Max Act: 5.6387. Min Act: -0.1700
Data Index: 4824375 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7949. Min Range: -5.7949
Max Act: 5.6387. Min Act: -0.1700
Data Index: 6909695 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7949. Min Range: -5.7949
Max Act: 5.6387. Min Act: -0.1700
Data Index: 2053317 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7949. Min Range: -5.7949
Max Act: 5.6387. Min Act: -0.1700
Data Index: 477506 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7949. Min Range: -5.7949
Max Act: 5.6074. Min Act: -0.1700
Data Index: 17941 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7949. Min Range: -5.7949
Max Act: 5.5762. Min Act: -0.1700
Data Index: 2864607 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7949. Min Range: -5.7949
Max Act: 5.5762. Min Act: -0.1700
Data Index: 8000748 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7949. Min Range: -5.7949
Max Act: 5.5762. Min Act: -0.1700
Data Index: 7619151 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7949. Min Range: -5.7949
Max Act: 5.5762. Min Act: -0.1700
Data Index: 1390275 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7949. Min Range: -5.7949
Max Act: 5.5762. Min Act: -0.1700
Data Index: 1494534 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7949. Min Range: -5.7949
Max Act: 5.5449. Min Act: -0.1700
Data Index: 1713153 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7949. Min Range: -5.7949
Max Act: 5.5762. Min Act: -0.1700
Data Index: 1517756 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19