Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9313. Min Range: -5.9313
Max Act: 5.9313. Min Act: -0.1700
Data Index: 7168146 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9313. Min Range: -5.9313
Max Act: 5.9313. Min Act: -0.1700
Data Index: 2108151 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9313. Min Range: -5.9313
Max Act: 5.9313. Min Act: -0.1700
Data Index: 1661171 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9313. Min Range: -5.9313
Max Act: 5.9000. Min Act: -0.1700
Data Index: 647011 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9313. Min Range: -5.9313
Max Act: 5.8375. Min Act: -0.1700
Data Index: 320135 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9313. Min Range: -5.9313
Max Act: 5.8375. Min Act: -0.1700
Data Index: 5280542 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9313. Min Range: -5.9313
Max Act: 5.8375. Min Act: -0.1700
Data Index: 2789720 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9313. Min Range: -5.9313
Max Act: 5.8063. Min Act: -0.1700
Data Index: 6020308 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9313. Min Range: -5.9313
Max Act: 5.8063. Min Act: -0.1700
Data Index: 194181 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9313. Min Range: -5.9313
Max Act: 5.7750. Min Act: -0.1700
Data Index: 4429393 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9313. Min Range: -5.9313
Max Act: 5.7750. Min Act: -0.1700
Data Index: 686850 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9313. Min Range: -5.9313
Max Act: 5.8063. Min Act: -0.1700
Data Index: 7915489 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9313. Min Range: -5.9313
Max Act: 5.7750. Min Act: -0.1700
Data Index: 4567206 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9313. Min Range: -5.9313
Max Act: 5.7125. Min Act: -0.1700
Data Index: 4363485 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9313. Min Range: -5.9313
Max Act: 5.7125. Min Act: -0.1700
Data Index: 7213235 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9313. Min Range: -5.9313
Max Act: 5.6813. Min Act: -0.1700
Data Index: 353858 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9313. Min Range: -5.9313
Max Act: 5.6813. Min Act: -0.1700
Data Index: 7329763 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9313. Min Range: -5.9313
Max Act: 5.6813. Min Act: -0.1700
Data Index: 250496 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9313. Min Range: -5.9313
Max Act: 5.6813. Min Act: -0.1700
Data Index: 2521341 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9313. Min Range: -5.9313
Max Act: 5.6813. Min Act: -0.1700
Data Index: 2404467 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19