Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1927 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2407. Min Range: -5.2407
Max Act: 5.2407. Min Act: -0.1700
Data Index: 47687 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2407. Min Range: -5.2407
Max Act: 5.1782. Min Act: -0.1700
Data Index: 5340934 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2407. Min Range: -5.2407
Max Act: 5.1782. Min Act: -0.1700
Data Index: 1565044 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2407. Min Range: -5.2407
Max Act: 5.1782. Min Act: -0.1700
Data Index: 3974918 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2407. Min Range: -5.2407
Max Act: 5.1470. Min Act: -0.1700
Data Index: 8716994 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2407. Min Range: -5.2407
Max Act: 5.1782. Min Act: -0.1700
Data Index: 5589025 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2407. Min Range: -5.2407
Max Act: 5.1470. Min Act: -0.1700
Data Index: 8053535 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2407. Min Range: -5.2407
Max Act: 5.1470. Min Act: -0.1700
Data Index: 4190430 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2407. Min Range: -5.2407
Max Act: 5.1157. Min Act: -0.1700
Data Index: 5926704 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2407. Min Range: -5.2407
Max Act: 5.1470. Min Act: -0.1700
Data Index: 8716993 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2407. Min Range: -5.2407
Max Act: 5.1157. Min Act: -0.1700
Data Index: 7929349 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2407. Min Range: -5.2407
Max Act: 5.0532. Min Act: -0.1700
Data Index: 3270013 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2407. Min Range: -5.2407
Max Act: 5.0532. Min Act: -0.1700
Data Index: 712744 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2407. Min Range: -5.2407
Max Act: 5.0532. Min Act: -0.1700
Data Index: 7921757 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2407. Min Range: -5.2407
Max Act: 5.0220. Min Act: -0.1700
Data Index: 5966832 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2407. Min Range: -5.2407
Max Act: 5.0220. Min Act: -0.1700
Data Index: 4318774 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2407. Min Range: -5.2407
Max Act: 5.0220. Min Act: -0.1700
Data Index: 6096247 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2407. Min Range: -5.2407
Max Act: 5.0220. Min Act: -0.1700
Data Index: 6828386 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2407. Min Range: -5.2407
Max Act: 5.0220. Min Act: -0.1700
Data Index: 2218429 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2407. Min Range: -5.2407
Max Act: 4.9907. Min Act: -0.1700
Data Index: 7862652 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19