Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4139 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8345. Min Range: -1.8345
Max Act: 1.8345. Min Act: -0.1700
Data Index: 6667030 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8345. Min Range: -1.8345
Max Act: 1.6617. Min Act: -0.1693
Data Index: 42922 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8345. Min Range: -1.8345
Max Act: 1.5920. Min Act: -0.1699
Data Index: 42923 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8345. Min Range: -1.8345
Max Act: 1.5570. Min Act: -0.1699
Data Index: 309622 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8345. Min Range: -1.8345
Max Act: 1.5570. Min Act: -0.1700
Data Index: 8207883 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8345. Min Range: -1.8345
Max Act: 1.5220. Min Act: -0.1700
Data Index: 4624784 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8345. Min Range: -1.8345
Max Act: 1.5044. Min Act: -0.1700
Data Index: 4624786 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8345. Min Range: -1.8345
Max Act: 1.5044. Min Act: -0.1700
Data Index: 4624785 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8345. Min Range: -1.8345
Max Act: 1.5044. Min Act: -0.1700
Data Index: 4624783 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8345. Min Range: -1.8345
Max Act: 1.5044. Min Act: -0.1700
Data Index: 4624776 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8345. Min Range: -1.8345
Max Act: 1.4693. Min Act: -0.1700
Data Index: 4624782 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8345. Min Range: -1.8345
Max Act: 1.4517. Min Act: -0.1700
Data Index: 4624780 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8345. Min Range: -1.8345
Max Act: 1.4517. Min Act: -0.1700
Data Index: 4624774 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8345. Min Range: -1.8345
Max Act: 1.4517. Min Act: -0.1700
Data Index: 4624781 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8345. Min Range: -1.8345
Max Act: 1.4165. Min Act: -0.1700
Data Index: 4624775 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8345. Min Range: -1.8345
Max Act: 1.3989. Min Act: -0.1700
Data Index: 4624779 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8345. Min Range: -1.8345
Max Act: 1.3813. Min Act: -0.1700
Data Index: 2215171 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8345. Min Range: -1.8345
Max Act: 1.3636. Min Act: -0.1700
Data Index: 4624778 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8345. Min Range: -1.8345
Max Act: 1.3460. Min Act: -0.1700
Data Index: 7165401 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8345. Min Range: -1.8345
Max Act: 1.3284. Min Act: -0.1700
Data Index: 5236296 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19