Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3165 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7307. Min Range: -5.7307
Max Act: 5.7307. Min Act: -0.1700
Data Index: 5719637 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7307. Min Range: -5.7307
Max Act: 5.6682. Min Act: -0.1700
Data Index: 1928031 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7307. Min Range: -5.7307
Max Act: 5.5432. Min Act: -0.1700
Data Index: 4956561 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7307. Min Range: -5.7307
Max Act: 5.4182. Min Act: -0.1700
Data Index: 2855997 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7307. Min Range: -5.7307
Max Act: 5.3870. Min Act: -0.1700
Data Index: 4230333 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7307. Min Range: -5.7307
Max Act: 5.3557. Min Act: -0.1700
Data Index: 2361471 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7307. Min Range: -5.7307
Max Act: 5.3557. Min Act: -0.1700
Data Index: 7453550 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7307. Min Range: -5.7307
Max Act: 5.2932. Min Act: -0.1700
Data Index: 4277002 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7307. Min Range: -5.7307
Max Act: 5.3245. Min Act: -0.1700
Data Index: 1935666 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7307. Min Range: -5.7307
Max Act: 5.2932. Min Act: -0.1700
Data Index: 2718929 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7307. Min Range: -5.7307
Max Act: 5.2620. Min Act: -0.1700
Data Index: 1060733 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7307. Min Range: -5.7307
Max Act: 5.2307. Min Act: -0.1700
Data Index: 4756930 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7307. Min Range: -5.7307
Max Act: 5.1682. Min Act: -0.1700
Data Index: 4537253 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7307. Min Range: -5.7307
Max Act: 5.1682. Min Act: -0.1700
Data Index: 8455924 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7307. Min Range: -5.7307
Max Act: 5.1370. Min Act: -0.1700
Data Index: 5030988 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7307. Min Range: -5.7307
Max Act: 5.1370. Min Act: -0.1700
Data Index: 3557908 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7307. Min Range: -5.7307
Max Act: 5.1057. Min Act: -0.1700
Data Index: 1089734 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7307. Min Range: -5.7307
Max Act: 5.1057. Min Act: -0.1700
Data Index: 6556078 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7307. Min Range: -5.7307
Max Act: 5.1057. Min Act: -0.1700
Data Index: 4125035 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7307. Min Range: -5.7307
Max Act: 5.1370. Min Act: -0.1700
Data Index: 6014365 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19