Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2072 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1108. Min Range: -5.1108
Max Act: 5.1108. Min Act: -0.1700
Data Index: 5645154 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1108. Min Range: -5.1108
Max Act: 5.0483. Min Act: -0.1700
Data Index: 4404014 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.9858. Min Act: -0.1700
Data Index: 3285738 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.9545. Min Act: -0.1700
Data Index: 5338858 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.8295. Min Act: -0.1700
Data Index: 57069 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.8295. Min Act: -0.1700
Data Index: 4884576 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.8295. Min Act: -0.1700
Data Index: 8279575 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.7358. Min Act: -0.1700
Data Index: 2516126 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.7358. Min Act: -0.1700
Data Index: 989634 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.6733. Min Act: -0.1700
Data Index: 5663826 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.6733. Min Act: -0.1700
Data Index: 4713936 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.6420. Min Act: -0.1700
Data Index: 4486731 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.6420. Min Act: -0.1700
Data Index: 5776770 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.6420. Min Act: -0.1700
Data Index: 6957064 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.5795. Min Act: -0.1700
Data Index: 7129350 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.6108. Min Act: -0.1700
Data Index: 3400258 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.5795. Min Act: -0.1700
Data Index: 7042838 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.6108. Min Act: -0.1700
Data Index: 6163091 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.6108. Min Act: -0.1700
Data Index: 8555400 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.6108. Min Act: -0.1700
Data Index: 635272 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19