Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2523 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5372. Min Range: -8.5372
Max Act: 8.5372. Min Act: -0.1700
Data Index: 1448783 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5372. Min Range: -8.5372
Max Act: 8.4747. Min Act: -0.1700
Data Index: 3638558 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5372. Min Range: -8.5372
Max Act: 8.4747. Min Act: -0.1700
Data Index: 7784425 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5372. Min Range: -8.5372
Max Act: 8.4747. Min Act: -0.1700
Data Index: 3880030 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5372. Min Range: -8.5372
Max Act: 8.2872. Min Act: -0.1700
Data Index: 5580800 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5372. Min Range: -8.5372
Max Act: 8.2247. Min Act: -0.1700
Data Index: 2859265 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5372. Min Range: -8.5372
Max Act: 8.2247. Min Act: -0.1700
Data Index: 2850050 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5372. Min Range: -8.5372
Max Act: 8.2247. Min Act: -0.1700
Data Index: 6642831 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5372. Min Range: -8.5372
Max Act: 8.2247. Min Act: -0.1700
Data Index: 8602250 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5372. Min Range: -8.5372
Max Act: 8.1622. Min Act: -0.1700
Data Index: 5586581 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5372. Min Range: -8.5372
Max Act: 8.1310. Min Act: -0.1700
Data Index: 3895435 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5372. Min Range: -8.5372
Max Act: 8.0997. Min Act: -0.1700
Data Index: 1018255 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5372. Min Range: -8.5372
Max Act: 8.0997. Min Act: -0.1700
Data Index: 5197697 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5372. Min Range: -8.5372
Max Act: 8.0685. Min Act: -0.1700
Data Index: 1351686 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5372. Min Range: -8.5372
Max Act: 8.0685. Min Act: -0.1700
Data Index: 1758060 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5372. Min Range: -8.5372
Max Act: 8.0685. Min Act: -0.1700
Data Index: 7494544 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5372. Min Range: -8.5372
Max Act: 8.0372. Min Act: -0.1700
Data Index: 5413435 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5372. Min Range: -8.5372
Max Act: 8.0372. Min Act: -0.1700
Data Index: 915225 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5372. Min Range: -8.5372
Max Act: 7.9747. Min Act: -0.1700
Data Index: 5050923 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5372. Min Range: -8.5372
Max Act: 7.9747. Min Act: -0.1700
Data Index: 5683967 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19