Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3568 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9297. Min Range: -8.9297
Max Act: 8.9297. Min Act: -0.1700
Data Index: 5837084 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9297. Min Range: -8.9297
Max Act: 8.9297. Min Act: -0.1700
Data Index: 6006148 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9297. Min Range: -8.9297
Max Act: 8.4922. Min Act: -0.1700
Data Index: 3456386 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9297. Min Range: -8.9297
Max Act: 8.4922. Min Act: -0.1700
Data Index: 604358 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9297. Min Range: -8.9297
Max Act: 8.4297. Min Act: -0.1700
Data Index: 3749269 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9297. Min Range: -8.9297
Max Act: 8.4297. Min Act: -0.1700
Data Index: 7124577 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9297. Min Range: -8.9297
Max Act: 8.4297. Min Act: -0.1700
Data Index: 5921909 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9297. Min Range: -8.9297
Max Act: 8.3672. Min Act: -0.1700
Data Index: 5881353 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9297. Min Range: -8.9297
Max Act: 8.3672. Min Act: -0.1700
Data Index: 7135477 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9297. Min Range: -8.9297
Max Act: 8.3672. Min Act: -0.1700
Data Index: 5611975 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9297. Min Range: -8.9297
Max Act: 8.3360. Min Act: -0.1700
Data Index: 5462832 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9297. Min Range: -8.9297
Max Act: 8.3360. Min Act: -0.1700
Data Index: 2055819 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9297. Min Range: -8.9297
Max Act: 8.3047. Min Act: -0.1700
Data Index: 7124580 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9297. Min Range: -8.9297
Max Act: 8.2735. Min Act: -0.1700
Data Index: 1171372 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9297. Min Range: -8.9297
Max Act: 8.3047. Min Act: -0.1700
Data Index: 7258740 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9297. Min Range: -8.9297
Max Act: 8.3047. Min Act: -0.1700
Data Index: 7124586 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9297. Min Range: -8.9297
Max Act: 8.3047. Min Act: -0.1700
Data Index: 3115006 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9297. Min Range: -8.9297
Max Act: 8.3047. Min Act: -0.1700
Data Index: 1852542 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9297. Min Range: -8.9297
Max Act: 8.3047. Min Act: -0.1700
Data Index: 6229197 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9297. Min Range: -8.9297
Max Act: 8.2735. Min Act: -0.1700
Data Index: 2055816 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19