Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2586 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6654. Min Range: -5.6654
Max Act: 5.6654. Min Act: -0.1700
Data Index: 901004 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6654. Min Range: -5.6654
Max Act: 5.4154. Min Act: -0.1700
Data Index: 1335293 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6654. Min Range: -5.6654
Max Act: 5.3842. Min Act: -0.1700
Data Index: 1114817 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6654. Min Range: -5.6654
Max Act: 5.2904. Min Act: -0.1700
Data Index: 7567554 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6654. Min Range: -5.6654
Max Act: 5.2592. Min Act: -0.1700
Data Index: 2618435 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6654. Min Range: -5.6654
Max Act: 5.2279. Min Act: -0.1700
Data Index: 1419136 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6654. Min Range: -5.6654
Max Act: 5.1967. Min Act: -0.1700
Data Index: 1591449 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6654. Min Range: -5.6654
Max Act: 5.1342. Min Act: -0.1700
Data Index: 7310871 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6654. Min Range: -5.6654
Max Act: 5.1342. Min Act: -0.1700
Data Index: 8007462 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6654. Min Range: -5.6654
Max Act: 5.1342. Min Act: -0.1700
Data Index: 3416589 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6654. Min Range: -5.6654
Max Act: 5.1342. Min Act: -0.1700
Data Index: 1436451 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6654. Min Range: -5.6654
Max Act: 5.1342. Min Act: -0.1700
Data Index: 2013126 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6654. Min Range: -5.6654
Max Act: 5.1342. Min Act: -0.1700
Data Index: 3329764 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6654. Min Range: -5.6654
Max Act: 5.1029. Min Act: -0.1700
Data Index: 2486611 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6654. Min Range: -5.6654
Max Act: 5.1029. Min Act: -0.1700
Data Index: 5574791 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6654. Min Range: -5.6654
Max Act: 5.0717. Min Act: -0.1700
Data Index: 5839862 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6654. Min Range: -5.6654
Max Act: 5.0717. Min Act: -0.1700
Data Index: 7836447 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6654. Min Range: -5.6654
Max Act: 5.0404. Min Act: -0.1700
Data Index: 4764537 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6654. Min Range: -5.6654
Max Act: 5.0092. Min Act: -0.1700
Data Index: 5714232 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6654. Min Range: -5.6654
Max Act: 5.0404. Min Act: -0.1700
Data Index: 6575956 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19