Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3518 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8317. Min Range: -5.8317
Max Act: 5.8317. Min Act: -0.1700
Data Index: 3211535 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8317. Min Range: -5.8317
Max Act: 5.8317. Min Act: -0.1700
Data Index: 3456421 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8317. Min Range: -5.8317
Max Act: 5.8004. Min Act: -0.1700
Data Index: 8068210 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8317. Min Range: -5.8317
Max Act: 5.7692. Min Act: -0.1700
Data Index: 3211536 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8317. Min Range: -5.8317
Max Act: 5.7692. Min Act: -0.1700
Data Index: 149148 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8317. Min Range: -5.8317
Max Act: 5.7692. Min Act: -0.1700
Data Index: 1810958 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8317. Min Range: -5.8317
Max Act: 5.7692. Min Act: -0.1700
Data Index: 7572880 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8317. Min Range: -5.8317
Max Act: 5.7379. Min Act: -0.1700
Data Index: 1816623 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8317. Min Range: -5.8317
Max Act: 5.7379. Min Act: -0.1700
Data Index: 4941651 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8317. Min Range: -5.8317
Max Act: 5.7379. Min Act: -0.1700
Data Index: 861570 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8317. Min Range: -5.8317
Max Act: 5.7379. Min Act: -0.1700
Data Index: 1331177 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8317. Min Range: -5.8317
Max Act: 5.7067. Min Act: -0.1700
Data Index: 8587048 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8317. Min Range: -5.8317
Max Act: 5.7067. Min Act: -0.1700
Data Index: 4136633 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8317. Min Range: -5.8317
Max Act: 5.7067. Min Act: -0.1700
Data Index: 6245284 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8317. Min Range: -5.8317
Max Act: 5.7067. Min Act: -0.1700
Data Index: 8358167 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8317. Min Range: -5.8317
Max Act: 5.7067. Min Act: -0.1700
Data Index: 6322817 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8317. Min Range: -5.8317
Max Act: 5.6754. Min Act: -0.1700
Data Index: 4241293 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8317. Min Range: -5.8317
Max Act: 5.6754. Min Act: -0.1700
Data Index: 6728646 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8317. Min Range: -5.8317
Max Act: 5.6754. Min Act: -0.1700
Data Index: 6364984 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8317. Min Range: -5.8317
Max Act: 5.6442. Min Act: -0.1700
Data Index: 3756571 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19