Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3590 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7254. Min Range: -4.7254
Max Act: 4.7254. Min Act: -0.1700
Data Index: 2270718 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7254. Min Range: -4.7254
Max Act: 4.6317. Min Act: -0.1700
Data Index: 7921846 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7254. Min Range: -4.7254
Max Act: 4.6317. Min Act: -0.1700
Data Index: 5633687 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7254. Min Range: -4.7254
Max Act: 4.6004. Min Act: -0.1700
Data Index: 3663499 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7254. Min Range: -4.7254
Max Act: 4.6004. Min Act: -0.1700
Data Index: 1856078 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7254. Min Range: -4.7254
Max Act: 4.5692. Min Act: -0.1700
Data Index: 4780964 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7254. Min Range: -4.7254
Max Act: 4.5692. Min Act: -0.1700
Data Index: 6215533 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7254. Min Range: -4.7254
Max Act: 4.5692. Min Act: -0.1700
Data Index: 8687573 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7254. Min Range: -4.7254
Max Act: 4.5692. Min Act: -0.1700
Data Index: 4425600 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7254. Min Range: -4.7254
Max Act: 4.5379. Min Act: -0.1700
Data Index: 659929 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7254. Min Range: -4.7254
Max Act: 4.5067. Min Act: -0.1700
Data Index: 6318845 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7254. Min Range: -4.7254
Max Act: 4.5379. Min Act: -0.1700
Data Index: 1950083 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7254. Min Range: -4.7254
Max Act: 4.5067. Min Act: -0.1700
Data Index: 3223149 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7254. Min Range: -4.7254
Max Act: 4.5067. Min Act: -0.1700
Data Index: 4653004 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7254. Min Range: -4.7254
Max Act: 4.5067. Min Act: -0.1700
Data Index: 4609220 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7254. Min Range: -4.7254
Max Act: 4.5379. Min Act: -0.1700
Data Index: 2792615 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7254. Min Range: -4.7254
Max Act: 4.5067. Min Act: -0.1700
Data Index: 4984602 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7254. Min Range: -4.7254
Max Act: 4.4754. Min Act: -0.1700
Data Index: 7175889 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7254. Min Range: -4.7254
Max Act: 4.4754. Min Act: -0.1700
Data Index: 7154849 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7254. Min Range: -4.7254
Max Act: 4.4754. Min Act: -0.1700
Data Index: 461292 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19