Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3284 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0779. Min Range: -7.0779
Max Act: 7.0779. Min Act: -0.1700
Data Index: 2936393 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0779. Min Range: -7.0779
Max Act: 6.7967. Min Act: -0.1700
Data Index: 644741 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0779. Min Range: -7.0779
Max Act: 6.7342. Min Act: -0.1700
Data Index: 401156 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0779. Min Range: -7.0779
Max Act: 6.6717. Min Act: -0.1700
Data Index: 7414457 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0779. Min Range: -7.0779
Max Act: 6.6717. Min Act: -0.1700
Data Index: 4966563 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0779. Min Range: -7.0779
Max Act: 6.6404. Min Act: -0.1700
Data Index: 2016627 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0779. Min Range: -7.0779
Max Act: 6.6404. Min Act: -0.1700
Data Index: 4354461 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0779. Min Range: -7.0779
Max Act: 6.6404. Min Act: -0.1700
Data Index: 261537 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0779. Min Range: -7.0779
Max Act: 6.5779. Min Act: -0.1700
Data Index: 149044 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0779. Min Range: -7.0779
Max Act: 6.5154. Min Act: -0.1700
Data Index: 6089528 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0779. Min Range: -7.0779
Max Act: 6.4842. Min Act: -0.1700
Data Index: 3392016 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0779. Min Range: -7.0779
Max Act: 6.4842. Min Act: -0.1700
Data Index: 7750210 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0779. Min Range: -7.0779
Max Act: 6.5154. Min Act: -0.1700
Data Index: 6813547 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0779. Min Range: -7.0779
Max Act: 6.4842. Min Act: -0.1700
Data Index: 8178154 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0779. Min Range: -7.0779
Max Act: 6.4529. Min Act: -0.1700
Data Index: 7489706 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0779. Min Range: -7.0779
Max Act: 6.4529. Min Act: -0.1700
Data Index: 3290718 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0779. Min Range: -7.0779
Max Act: 6.4217. Min Act: -0.1700
Data Index: 4157072 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0779. Min Range: -7.0779
Max Act: 6.3904. Min Act: -0.1700
Data Index: 7052226 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0779. Min Range: -7.0779
Max Act: 6.3904. Min Act: -0.1700
Data Index: 5555788 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0779. Min Range: -7.0779
Max Act: 6.4217. Min Act: -0.1700
Data Index: 7887564 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19