Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3111 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1165. Min Range: -9.1165
Max Act: 9.1165. Min Act: -0.1700
Data Index: 7319649 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1165. Min Range: -9.1165
Max Act: 8.9290. Min Act: -0.1700
Data Index: 5127125 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1165. Min Range: -9.1165
Max Act: 8.8665. Min Act: -0.1700
Data Index: 8377250 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1165. Min Range: -9.1165
Max Act: 8.8040. Min Act: -0.1700
Data Index: 5612386 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1165. Min Range: -9.1165
Max Act: 8.6790. Min Act: -0.1700
Data Index: 6750915 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1165. Min Range: -9.1165
Max Act: 8.6165. Min Act: -0.1700
Data Index: 910252 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1165. Min Range: -9.1165
Max Act: 8.6165. Min Act: -0.1700
Data Index: 5336526 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1165. Min Range: -9.1165
Max Act: 8.6165. Min Act: -0.1700
Data Index: 3827296 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1165. Min Range: -9.1165
Max Act: 8.6165. Min Act: -0.1700
Data Index: 6574810 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1165. Min Range: -9.1165
Max Act: 8.5540. Min Act: -0.1700
Data Index: 8477155 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1165. Min Range: -9.1165
Max Act: 8.5540. Min Act: -0.1700
Data Index: 6749411 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1165. Min Range: -9.1165
Max Act: 8.5540. Min Act: -0.1700
Data Index: 1828609 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1165. Min Range: -9.1165
Max Act: 8.5540. Min Act: -0.1700
Data Index: 5408020 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1165. Min Range: -9.1165
Max Act: 8.5540. Min Act: -0.1700
Data Index: 6703813 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1165. Min Range: -9.1165
Max Act: 8.4915. Min Act: -0.1700
Data Index: 2468274 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1165. Min Range: -9.1165
Max Act: 8.4915. Min Act: -0.1700
Data Index: 4548218 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1165. Min Range: -9.1165
Max Act: 8.4915. Min Act: -0.1700
Data Index: 2320805 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1165. Min Range: -9.1165
Max Act: 8.4915. Min Act: -0.1700
Data Index: 5394860 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1165. Min Range: -9.1165
Max Act: 8.4915. Min Act: -0.1700
Data Index: 1435126 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1165. Min Range: -9.1165
Max Act: 8.5540. Min Act: -0.1700
Data Index: 1025200 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19