Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3334 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0129. Min Range: -6.0129
Max Act: 6.0129. Min Act: -0.1700
Data Index: 3163496 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0129. Min Range: -6.0129
Max Act: 6.0129. Min Act: -0.1700
Data Index: 4440418 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0129. Min Range: -6.0129
Max Act: 5.9192. Min Act: -0.1700
Data Index: 4878226 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0129. Min Range: -6.0129
Max Act: 5.8567. Min Act: -0.1700
Data Index: 3282059 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0129. Min Range: -6.0129
Max Act: 5.8567. Min Act: -0.1700
Data Index: 6635632 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0129. Min Range: -6.0129
Max Act: 5.7942. Min Act: -0.1700
Data Index: 2256612 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0129. Min Range: -6.0129
Max Act: 5.7942. Min Act: -0.1700
Data Index: 822340 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0129. Min Range: -6.0129
Max Act: 5.7317. Min Act: -0.1700
Data Index: 4955995 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0129. Min Range: -6.0129
Max Act: 5.7629. Min Act: -0.1700
Data Index: 7038742 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0129. Min Range: -6.0129
Max Act: 5.7629. Min Act: -0.1700
Data Index: 1840391 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0129. Min Range: -6.0129
Max Act: 5.7317. Min Act: -0.1700
Data Index: 6033177 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0129. Min Range: -6.0129
Max Act: 5.7629. Min Act: -0.1700
Data Index: 420551 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0129. Min Range: -6.0129
Max Act: 5.7317. Min Act: -0.1700
Data Index: 4708362 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0129. Min Range: -6.0129
Max Act: 5.7004. Min Act: -0.1700
Data Index: 3452344 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0129. Min Range: -6.0129
Max Act: 5.7004. Min Act: -0.1700
Data Index: 3391843 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0129. Min Range: -6.0129
Max Act: 5.7004. Min Act: -0.1700
Data Index: 7285294 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0129. Min Range: -6.0129
Max Act: 5.7004. Min Act: -0.1700
Data Index: 6389638 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0129. Min Range: -6.0129
Max Act: 5.6692. Min Act: -0.1700
Data Index: 843478 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0129. Min Range: -6.0129
Max Act: 5.6692. Min Act: -0.1700
Data Index: 43014 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0129. Min Range: -6.0129
Max Act: 5.6692. Min Act: -0.1700
Data Index: 5877259 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19