Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3376 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.5687. Min Act: -0.1700
Data Index: 4680116 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.5062. Min Act: -0.1700
Data Index: 458115 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.4437. Min Act: -0.1700
Data Index: 3337415 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.4125. Min Act: -0.1700
Data Index: 2153293 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.3500. Min Act: -0.1700
Data Index: 7980330 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.3812. Min Act: -0.1700
Data Index: 7865592 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.3812. Min Act: -0.1700
Data Index: 7111578 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.3812. Min Act: -0.1700
Data Index: 8408154 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.3500. Min Act: -0.1700
Data Index: 4390424 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.3500. Min Act: -0.1700
Data Index: 4215009 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.3500. Min Act: -0.1700
Data Index: 4884849 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.3500. Min Act: -0.1700
Data Index: 5715340 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.3500. Min Act: -0.1700
Data Index: 2478841 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.3500. Min Act: -0.1700
Data Index: 4215015 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.3187. Min Act: -0.1700
Data Index: 1424337 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.3500. Min Act: -0.1700
Data Index: 6110160 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.3187. Min Act: -0.1700
Data Index: 6128082 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.3187. Min Act: -0.1700
Data Index: 6551614 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.3187. Min Act: -0.1700
Data Index: 2085709 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.2874. Min Act: -0.1700
Data Index: 3955755 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19