Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2721 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5040. Min Range: -9.5040
Max Act: 9.5040. Min Act: -0.1700
Data Index: 3309016 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5040. Min Range: -9.5040
Max Act: 9.2540. Min Act: -0.1700
Data Index: 2067458 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5040. Min Range: -9.5040
Max Act: 9.1915. Min Act: -0.1700
Data Index: 3228301 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5040. Min Range: -9.5040
Max Act: 9.1290. Min Act: -0.1700
Data Index: 6374040 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5040. Min Range: -9.5040
Max Act: 9.0040. Min Act: -0.1700
Data Index: 4748644 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5040. Min Range: -9.5040
Max Act: 9.0040. Min Act: -0.1700
Data Index: 4603932 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5040. Min Range: -9.5040
Max Act: 8.9415. Min Act: -0.1700
Data Index: 4901523 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5040. Min Range: -9.5040
Max Act: 8.9415. Min Act: -0.1700
Data Index: 8344394 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5040. Min Range: -9.5040
Max Act: 8.9415. Min Act: -0.1700
Data Index: 6426947 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5040. Min Range: -9.5040
Max Act: 8.8790. Min Act: -0.1700
Data Index: 1035066 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5040. Min Range: -9.5040
Max Act: 8.8165. Min Act: -0.1700
Data Index: 6209698 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5040. Min Range: -9.5040
Max Act: 8.8165. Min Act: -0.1700
Data Index: 7706238 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5040. Min Range: -9.5040
Max Act: 8.8165. Min Act: -0.1700
Data Index: 2859378 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5040. Min Range: -9.5040
Max Act: 8.8165. Min Act: -0.1700
Data Index: 6323861 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5040. Min Range: -9.5040
Max Act: 8.8165. Min Act: -0.1700
Data Index: 5908218 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5040. Min Range: -9.5040
Max Act: 8.7540. Min Act: -0.1700
Data Index: 4018078 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5040. Min Range: -9.5040
Max Act: 8.7540. Min Act: -0.1700
Data Index: 6308422 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5040. Min Range: -9.5040
Max Act: 8.7540. Min Act: -0.1700
Data Index: 844587 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5040. Min Range: -9.5040
Max Act: 8.6290. Min Act: -0.1700
Data Index: 271253 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5040. Min Range: -9.5040
Max Act: 8.6290. Min Act: -0.1700
Data Index: 6353030 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19