Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 521 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0553. Min Range: -4.0553
Max Act: 4.0553. Min Act: -0.1700
Data Index: 3865327 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0553. Min Range: -4.0553
Max Act: 3.9928. Min Act: -0.1700
Data Index: 6241891 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0553. Min Range: -4.0553
Max Act: 3.9928. Min Act: -0.1700
Data Index: 6185033 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0553. Min Range: -4.0553
Max Act: 3.8990. Min Act: -0.1700
Data Index: 3686280 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0553. Min Range: -4.0553
Max Act: 3.8990. Min Act: -0.1700
Data Index: 834867 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0553. Min Range: -4.0553
Max Act: 3.8990. Min Act: -0.1700
Data Index: 5845177 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0553. Min Range: -4.0553
Max Act: 3.8364. Min Act: -0.1700
Data Index: 5120516 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0553. Min Range: -4.0553
Max Act: 3.8677. Min Act: -0.1700
Data Index: 4358244 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0553. Min Range: -4.0553
Max Act: 3.8677. Min Act: -0.1700
Data Index: 8225765 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0553. Min Range: -4.0553
Max Act: 3.8677. Min Act: -0.1700
Data Index: 5985315 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0553. Min Range: -4.0553
Max Act: 3.8052. Min Act: -0.1700
Data Index: 8135273 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0553. Min Range: -4.0553
Max Act: 3.8208. Min Act: -0.1700
Data Index: 4020036 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0553. Min Range: -4.0553
Max Act: 3.8052. Min Act: -0.1700
Data Index: 4494262 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0553. Min Range: -4.0553
Max Act: 3.8052. Min Act: -0.1700
Data Index: 2551842 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0553. Min Range: -4.0553
Max Act: 3.7895. Min Act: -0.1700
Data Index: 2331917 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0553. Min Range: -4.0553
Max Act: 3.8052. Min Act: -0.1700
Data Index: 6046949 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0553. Min Range: -4.0553
Max Act: 3.7895. Min Act: -0.1700
Data Index: 2252443 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0553. Min Range: -4.0553
Max Act: 3.7895. Min Act: -0.1700
Data Index: 6801063 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0553. Min Range: -4.0553
Max Act: 3.7895. Min Act: -0.1700
Data Index: 1372182 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0553. Min Range: -4.0553
Max Act: 3.7739. Min Act: -0.1700
Data Index: 3675907 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19