Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4340 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4017. Min Range: -7.4017
Max Act: 7.4017. Min Act: -0.1700
Data Index: 3866321 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4017. Min Range: -7.4017
Max Act: 7.3392. Min Act: -0.1700
Data Index: 113862 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4017. Min Range: -7.4017
Max Act: 7.3392. Min Act: -0.1700
Data Index: 8786663 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4017. Min Range: -7.4017
Max Act: 7.2767. Min Act: -0.1700
Data Index: 3655043 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4017. Min Range: -7.4017
Max Act: 7.2767. Min Act: -0.1700
Data Index: 7679992 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4017. Min Range: -7.4017
Max Act: 7.2767. Min Act: -0.1700
Data Index: 2966812 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4017. Min Range: -7.4017
Max Act: 7.2767. Min Act: -0.1700
Data Index: 2108458 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4017. Min Range: -7.4017
Max Act: 7.2767. Min Act: -0.1700
Data Index: 7236426 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4017. Min Range: -7.4017
Max Act: 7.2767. Min Act: -0.1700
Data Index: 7172764 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4017. Min Range: -7.4017
Max Act: 7.2142. Min Act: -0.1700
Data Index: 6144974 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4017. Min Range: -7.4017
Max Act: 7.1517. Min Act: -0.1700
Data Index: 7150752 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4017. Min Range: -7.4017
Max Act: 7.0892. Min Act: -0.1700
Data Index: 6528679 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4017. Min Range: -7.4017
Max Act: 7.0580. Min Act: -0.1700
Data Index: 1638342 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4017. Min Range: -7.4017
Max Act: 7.0267. Min Act: -0.1700
Data Index: 4675295 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4017. Min Range: -7.4017
Max Act: 7.0267. Min Act: -0.1700
Data Index: 6902642 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4017. Min Range: -7.4017
Max Act: 6.9955. Min Act: -0.1700
Data Index: 7090908 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4017. Min Range: -7.4017
Max Act: 6.9955. Min Act: -0.1700
Data Index: 1512467 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4017. Min Range: -7.4017
Max Act: 6.9642. Min Act: -0.1700
Data Index: 4871571 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4017. Min Range: -7.4017
Max Act: 6.9330. Min Act: -0.1700
Data Index: 3965611 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4017. Min Range: -7.4017
Max Act: 6.9330. Min Act: -0.1700
Data Index: 4488965 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19