Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5791 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.8101. Min Act: -0.1700
Data Index: 5879773 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.7476. Min Act: -0.1700
Data Index: 4529824 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.6851. Min Act: -0.1700
Data Index: 5994490 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.6851. Min Act: -0.1700
Data Index: 475120 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.6851. Min Act: -0.1700
Data Index: 8593253 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.6851. Min Act: -0.1700
Data Index: 1019800 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.6226. Min Act: -0.1700
Data Index: 7574822 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.5914. Min Act: -0.1700
Data Index: 6486381 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.6226. Min Act: -0.1700
Data Index: 8559348 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.5914. Min Act: -0.1700
Data Index: 821940 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.5601. Min Act: -0.1700
Data Index: 3852224 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.5289. Min Act: -0.1700
Data Index: 1156746 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.5289. Min Act: -0.1700
Data Index: 4112789 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.5289. Min Act: -0.1700
Data Index: 6148754 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.5289. Min Act: -0.1700
Data Index: 2417645 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.4664. Min Act: -0.1700
Data Index: 5049843 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.4976. Min Act: -0.1700
Data Index: 449165 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.4976. Min Act: -0.1700
Data Index: 4990900 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.4664. Min Act: -0.1700
Data Index: 694248 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.4351. Min Act: -0.1700
Data Index: 7517035 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19