Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2919 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1187. Min Range: -4.1187
Max Act: 4.1187. Min Act: -0.1700
Data Index: 232290 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1187. Min Range: -4.1187
Max Act: 3.9937. Min Act: -0.1700
Data Index: 535528 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1187. Min Range: -4.1187
Max Act: 3.8999. Min Act: -0.1700
Data Index: 6378641 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1187. Min Range: -4.1187
Max Act: 3.8374. Min Act: -0.1700
Data Index: 1354540 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1187. Min Range: -4.1187
Max Act: 3.8374. Min Act: -0.1700
Data Index: 5641953 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1187. Min Range: -4.1187
Max Act: 3.8374. Min Act: -0.1700
Data Index: 2474627 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1187. Min Range: -4.1187
Max Act: 3.8374. Min Act: -0.1700
Data Index: 3945081 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1187. Min Range: -4.1187
Max Act: 3.7748. Min Act: -0.1700
Data Index: 1458664 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1187. Min Range: -4.1187
Max Act: 3.7435. Min Act: -0.1700
Data Index: 8640828 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1187. Min Range: -4.1187
Max Act: 3.7435. Min Act: -0.1700
Data Index: 7291908 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1187. Min Range: -4.1187
Max Act: 3.7748. Min Act: -0.1700
Data Index: 6480843 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1187. Min Range: -4.1187
Max Act: 3.7435. Min Act: -0.1700
Data Index: 6619574 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1187. Min Range: -4.1187
Max Act: 3.7435. Min Act: -0.1700
Data Index: 5473787 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1187. Min Range: -4.1187
Max Act: 3.7748. Min Act: -0.1700
Data Index: 8314644 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1187. Min Range: -4.1187
Max Act: 3.7123. Min Act: -0.1700
Data Index: 4275543 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1187. Min Range: -4.1187
Max Act: 3.7123. Min Act: -0.1700
Data Index: 6580477 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1187. Min Range: -4.1187
Max Act: 3.7123. Min Act: -0.1700
Data Index: 7750315 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1187. Min Range: -4.1187
Max Act: 3.6810. Min Act: -0.1700
Data Index: 3336375 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1187. Min Range: -4.1187
Max Act: 3.6810. Min Act: -0.1700
Data Index: 2170376 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1187. Min Range: -4.1187
Max Act: 3.7123. Min Act: -0.1700
Data Index: 7060929 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19