Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5426 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9164. Min Range: -4.9164
Max Act: 4.8851. Min Act: -0.1700
Data Index: 2980074 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9164. Min Range: -4.9164
Max Act: 4.9164. Min Act: -0.1700
Data Index: 556747 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9164. Min Range: -4.9164
Max Act: 4.8539. Min Act: -0.1700
Data Index: 6526390 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9164. Min Range: -4.9164
Max Act: 4.8226. Min Act: -0.1700
Data Index: 1093114 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9164. Min Range: -4.9164
Max Act: 4.8226. Min Act: -0.1700
Data Index: 2884773 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9164. Min Range: -4.9164
Max Act: 4.8226. Min Act: -0.1700
Data Index: 6691066 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9164. Min Range: -4.9164
Max Act: 4.8226. Min Act: -0.1700
Data Index: 3482503 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9164. Min Range: -4.9164
Max Act: 4.8226. Min Act: -0.1700
Data Index: 2224981 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9164. Min Range: -4.9164
Max Act: 4.7914. Min Act: -0.1700
Data Index: 5956933 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9164. Min Range: -4.9164
Max Act: 4.7914. Min Act: -0.1700
Data Index: 7096097 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9164. Min Range: -4.9164
Max Act: 4.7914. Min Act: -0.1700
Data Index: 5949360 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9164. Min Range: -4.9164
Max Act: 4.7914. Min Act: -0.1700
Data Index: 7737302 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9164. Min Range: -4.9164
Max Act: 4.7601. Min Act: -0.1700
Data Index: 1423322 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9164. Min Range: -4.9164
Max Act: 4.7601. Min Act: -0.1700
Data Index: 2529850 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9164. Min Range: -4.9164
Max Act: 4.7601. Min Act: -0.1700
Data Index: 3191852 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9164. Min Range: -4.9164
Max Act: 4.7289. Min Act: -0.1700
Data Index: 2729179 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9164. Min Range: -4.9164
Max Act: 4.7289. Min Act: -0.1700
Data Index: 4087569 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9164. Min Range: -4.9164
Max Act: 4.7289. Min Act: -0.1700
Data Index: 7618819 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9164. Min Range: -4.9164
Max Act: 4.6976. Min Act: -0.1700
Data Index: 3508372 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9164. Min Range: -4.9164
Max Act: 4.6976. Min Act: -0.1700
Data Index: 4265438 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19