Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5425 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.8164. Min Act: -0.1700
Data Index: 7439978 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.7851. Min Act: -0.1700
Data Index: 954351 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.6600. Min Act: -0.1700
Data Index: 2275311 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.4565. Min Act: -0.1700
Data Index: 5732752 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.4408. Min Act: -0.1700
Data Index: 5528662 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.4251. Min Act: -0.1700
Data Index: 5771182 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.4094. Min Act: -0.1700
Data Index: 708713 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.3781. Min Act: -0.1700
Data Index: 1879688 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.3310. Min Act: -0.1700
Data Index: 5087910 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.3467. Min Act: -0.1700
Data Index: 859988 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.3467. Min Act: -0.1700
Data Index: 8502844 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.3467. Min Act: -0.1700
Data Index: 7402495 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.3153. Min Act: -0.1700
Data Index: 1991771 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.2839. Min Act: -0.1700
Data Index: 7781257 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.2682. Min Act: -0.1700
Data Index: 156837 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.2682. Min Act: -0.1700
Data Index: 781769 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.2525. Min Act: -0.1700
Data Index: 7324163 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.2682. Min Act: -0.1700
Data Index: 5832049 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.2525. Min Act: -0.1700
Data Index: 2254064 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.2525. Min Act: -0.1700
Data Index: 5040313 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19