Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6368 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9152. Min Range: -10.9152
Max Act: 10.9152. Min Act: -0.1700
Data Index: 8109320 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9152. Min Range: -10.9152
Max Act: 9.9152. Min Act: -0.1700
Data Index: 6364784 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9152. Min Range: -10.9152
Max Act: 9.3527. Min Act: -0.1700
Data Index: 5244127 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9152. Min Range: -10.9152
Max Act: 9.2277. Min Act: -0.1700
Data Index: 2525632 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9152. Min Range: -10.9152
Max Act: 9.2277. Min Act: -0.1700
Data Index: 6753848 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9152. Min Range: -10.9152
Max Act: 9.1027. Min Act: -0.1700
Data Index: 8551893 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9152. Min Range: -10.9152
Max Act: 9.1027. Min Act: -0.1700
Data Index: 7996691 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9152. Min Range: -10.9152
Max Act: 9.0402. Min Act: -0.1700
Data Index: 8353882 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9152. Min Range: -10.9152
Max Act: 9.0402. Min Act: -0.1700
Data Index: 606253 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9152. Min Range: -10.9152
Max Act: 9.0402. Min Act: -0.1700
Data Index: 5417483 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9152. Min Range: -10.9152
Max Act: 9.0402. Min Act: -0.1700
Data Index: 1460953 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9152. Min Range: -10.9152
Max Act: 9.0402. Min Act: -0.1700
Data Index: 1103565 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9152. Min Range: -10.9152
Max Act: 9.0402. Min Act: -0.1700
Data Index: 3660280 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9152. Min Range: -10.9152
Max Act: 8.9152. Min Act: -0.1700
Data Index: 4645273 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9152. Min Range: -10.9152
Max Act: 8.9152. Min Act: -0.1700
Data Index: 4729909 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9152. Min Range: -10.9152
Max Act: 8.8527. Min Act: -0.1700
Data Index: 783598 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9152. Min Range: -10.9152
Max Act: 8.8527. Min Act: -0.1700
Data Index: 3076024 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9152. Min Range: -10.9152
Max Act: 8.8527. Min Act: -0.1700
Data Index: 2702806 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9152. Min Range: -10.9152
Max Act: 8.8527. Min Act: -0.1700
Data Index: 7970870 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9152. Min Range: -10.9152
Max Act: 8.8527. Min Act: -0.1700
Data Index: 6567284 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19