Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2218 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5491. Min Range: -9.5491
Max Act: 9.5491. Min Act: -0.1700
Data Index: 7522891 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5491. Min Range: -9.5491
Max Act: 9.4241. Min Act: -0.1700
Data Index: 7226874 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5491. Min Range: -9.5491
Max Act: 9.4241. Min Act: -0.1700
Data Index: 300319 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5491. Min Range: -9.5491
Max Act: 9.1116. Min Act: -0.1700
Data Index: 5638357 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5491. Min Range: -9.5491
Max Act: 8.9866. Min Act: -0.1700
Data Index: 4440527 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5491. Min Range: -9.5491
Max Act: 8.9241. Min Act: -0.1700
Data Index: 6311034 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5491. Min Range: -9.5491
Max Act: 8.9241. Min Act: -0.1700
Data Index: 6311044 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5491. Min Range: -9.5491
Max Act: 8.8616. Min Act: -0.1700
Data Index: 7806748 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5491. Min Range: -9.5491
Max Act: 8.8616. Min Act: -0.1700
Data Index: 4142908 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5491. Min Range: -9.5491
Max Act: 8.8616. Min Act: -0.1700
Data Index: 1679598 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5491. Min Range: -9.5491
Max Act: 8.7991. Min Act: -0.1700
Data Index: 3336914 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5491. Min Range: -9.5491
Max Act: 8.7366. Min Act: -0.1700
Data Index: 5686834 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5491. Min Range: -9.5491
Max Act: 8.7366. Min Act: -0.1700
Data Index: 4007541 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5491. Min Range: -9.5491
Max Act: 8.7366. Min Act: -0.1700
Data Index: 5607372 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5491. Min Range: -9.5491
Max Act: 8.7366. Min Act: -0.1700
Data Index: 5872411 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5491. Min Range: -9.5491
Max Act: 8.7366. Min Act: -0.1700
Data Index: 5197208 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5491. Min Range: -9.5491
Max Act: 8.6741. Min Act: -0.1700
Data Index: 3016735 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5491. Min Range: -9.5491
Max Act: 8.6116. Min Act: -0.1700
Data Index: 2851751 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5491. Min Range: -9.5491
Max Act: 8.6116. Min Act: -0.1700
Data Index: 1736602 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5491. Min Range: -9.5491
Max Act: 8.6116. Min Act: -0.1700
Data Index: 1079922 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19