Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3426 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1468. Min Range: -8.1468
Max Act: 8.1468. Min Act: -0.1700
Data Index: 4917360 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1468. Min Range: -8.1468
Max Act: 8.0843. Min Act: -0.1700
Data Index: 120148 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1468. Min Range: -8.1468
Max Act: 8.0843. Min Act: -0.1700
Data Index: 7743094 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1468. Min Range: -8.1468
Max Act: 8.0218. Min Act: -0.1700
Data Index: 1063118 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1468. Min Range: -8.1468
Max Act: 8.0218. Min Act: -0.1700
Data Index: 2004796 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1468. Min Range: -8.1468
Max Act: 7.8968. Min Act: -0.1700
Data Index: 2668447 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1468. Min Range: -8.1468
Max Act: 7.8656. Min Act: -0.1700
Data Index: 7200125 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1468. Min Range: -8.1468
Max Act: 7.8031. Min Act: -0.1700
Data Index: 2313617 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1468. Min Range: -8.1468
Max Act: 7.7406. Min Act: -0.1700
Data Index: 1377936 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1468. Min Range: -8.1468
Max Act: 7.7093. Min Act: -0.1700
Data Index: 55466 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1468. Min Range: -8.1468
Max Act: 7.7406. Min Act: -0.1700
Data Index: 6003239 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1468. Min Range: -8.1468
Max Act: 7.7093. Min Act: -0.1700
Data Index: 3892269 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1468. Min Range: -8.1468
Max Act: 7.7093. Min Act: -0.1699
Data Index: 419621 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1468. Min Range: -8.1468
Max Act: 7.7093. Min Act: -0.1700
Data Index: 2337388 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1468. Min Range: -8.1468
Max Act: 7.6468. Min Act: -0.1700
Data Index: 6840858 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1468. Min Range: -8.1468
Max Act: 7.6468. Min Act: -0.1700
Data Index: 4395797 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1468. Min Range: -8.1468
Max Act: 7.6781. Min Act: -0.1700
Data Index: 3502622 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1468. Min Range: -8.1468
Max Act: 7.6156. Min Act: -0.1700
Data Index: 3442471 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1468. Min Range: -8.1468
Max Act: 7.5843. Min Act: -0.1700
Data Index: 178770 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1468. Min Range: -8.1468
Max Act: 7.6468. Min Act: -0.1700
Data Index: 6805630 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19