Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1837 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7018. Min Range: -5.7018
Max Act: 5.7018. Min Act: -0.1700
Data Index: 1254490 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7018. Min Range: -5.7018
Max Act: 5.6706. Min Act: -0.1700
Data Index: 3070454 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7018. Min Range: -5.7018
Max Act: 5.4831. Min Act: -0.1700
Data Index: 5877085 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7018. Min Range: -5.7018
Max Act: 5.4518. Min Act: -0.1700
Data Index: 3252234 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7018. Min Range: -5.7018
Max Act: 5.3893. Min Act: -0.1700
Data Index: 6151092 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7018. Min Range: -5.7018
Max Act: 5.3268. Min Act: -0.1700
Data Index: 6555245 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7018. Min Range: -5.7018
Max Act: 5.3581. Min Act: -0.1700
Data Index: 2459523 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7018. Min Range: -5.7018
Max Act: 5.3268. Min Act: -0.1700
Data Index: 6422749 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7018. Min Range: -5.7018
Max Act: 5.3268. Min Act: -0.1700
Data Index: 8728288 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7018. Min Range: -5.7018
Max Act: 5.3268. Min Act: -0.1700
Data Index: 8607953 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7018. Min Range: -5.7018
Max Act: 5.3268. Min Act: -0.1700
Data Index: 8728287 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7018. Min Range: -5.7018
Max Act: 5.2956. Min Act: -0.1700
Data Index: 8086073 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7018. Min Range: -5.7018
Max Act: 5.2956. Min Act: -0.1700
Data Index: 3918525 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7018. Min Range: -5.7018
Max Act: 5.2643. Min Act: -0.1700
Data Index: 8375580 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7018. Min Range: -5.7018
Max Act: 5.2643. Min Act: -0.1700
Data Index: 1279090 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7018. Min Range: -5.7018
Max Act: 5.2643. Min Act: -0.1700
Data Index: 8224122 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7018. Min Range: -5.7018
Max Act: 5.2643. Min Act: -0.1700
Data Index: 6042423 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7018. Min Range: -5.7018
Max Act: 5.2643. Min Act: -0.1700
Data Index: 6538387 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7018. Min Range: -5.7018
Max Act: 5.2331. Min Act: -0.1700
Data Index: 1744873 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7018. Min Range: -5.7018
Max Act: 5.2331. Min Act: -0.1700
Data Index: 185565 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19