Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 883 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9081. Min Range: -5.9081
Max Act: 5.9081. Min Act: -0.1700
Data Index: 1547540 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9081. Min Range: -5.9081
Max Act: 5.8769. Min Act: -0.1700
Data Index: 5230179 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9081. Min Range: -5.9081
Max Act: 5.8769. Min Act: -0.1700
Data Index: 5826208 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9081. Min Range: -5.9081
Max Act: 5.8144. Min Act: -0.1700
Data Index: 6177079 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9081. Min Range: -5.9081
Max Act: 5.8144. Min Act: -0.1700
Data Index: 4382607 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9081. Min Range: -5.9081
Max Act: 5.7831. Min Act: -0.1700
Data Index: 6682151 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9081. Min Range: -5.9081
Max Act: 5.7831. Min Act: -0.1700
Data Index: 2835896 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9081. Min Range: -5.9081
Max Act: 5.7519. Min Act: -0.1700
Data Index: 7441068 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9081. Min Range: -5.9081
Max Act: 5.7519. Min Act: -0.1700
Data Index: 4688464 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9081. Min Range: -5.9081
Max Act: 5.7206. Min Act: -0.1700
Data Index: 6445722 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9081. Min Range: -5.9081
Max Act: 5.7206. Min Act: -0.1700
Data Index: 3342469 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9081. Min Range: -5.9081
Max Act: 5.7206. Min Act: -0.1700
Data Index: 7634273 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9081. Min Range: -5.9081
Max Act: 5.6894. Min Act: -0.1700
Data Index: 2387428 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9081. Min Range: -5.9081
Max Act: 5.6581. Min Act: -0.1700
Data Index: 316988 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9081. Min Range: -5.9081
Max Act: 5.6581. Min Act: -0.1700
Data Index: 4142895 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9081. Min Range: -5.9081
Max Act: 5.6581. Min Act: -0.1700
Data Index: 3514778 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9081. Min Range: -5.9081
Max Act: 5.6269. Min Act: -0.1700
Data Index: 3017813 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9081. Min Range: -5.9081
Max Act: 5.6269. Min Act: -0.1700
Data Index: 4050337 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9081. Min Range: -5.9081
Max Act: 5.5956. Min Act: -0.1700
Data Index: 2435629 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9081. Min Range: -5.9081
Max Act: 5.5956. Min Act: -0.1700
Data Index: 6669711 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #19