Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1586 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.8793. Min Act: -0.1700
Data Index: 7047288 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.8793. Min Act: -0.1700
Data Index: 4374219 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.2855. Min Act: -0.1700
Data Index: 8104554 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.1918. Min Act: -0.1700
Data Index: 7954083 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.1918. Min Act: -0.1700
Data Index: 6907224 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.1918. Min Act: -0.1700
Data Index: 4949504 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.0980. Min Act: -0.1700
Data Index: 8085400 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.1293. Min Act: -0.1700
Data Index: 5583841 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.0980. Min Act: -0.1700
Data Index: 7059115 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.0980. Min Act: -0.1700
Data Index: 3187498 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.0668. Min Act: -0.1700
Data Index: 7919645 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.0668. Min Act: -0.1700
Data Index: 2132003 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.0355. Min Act: -0.1700
Data Index: 6467405 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.0043. Min Act: -0.1700
Data Index: 7419515 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.0043. Min Act: -0.1700
Data Index: 1958113 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.0043. Min Act: -0.1700
Data Index: 3304377 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.0043. Min Act: -0.1700
Data Index: 8089150 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.0043. Min Act: -0.1700
Data Index: 1604502 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.0355. Min Act: -0.1700
Data Index: 6538505 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8793. Min Range: -6.8793
Max Act: 5.9730. Min Act: -0.1700
Data Index: 6080049 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19