Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4946 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0165. Min Range: -6.0165
Max Act: 6.0165. Min Act: -0.1700
Data Index: 8506097 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0165. Min Range: -6.0165
Max Act: 5.9852. Min Act: -0.1700
Data Index: 3301182 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0165. Min Range: -6.0165
Max Act: 5.8602. Min Act: -0.1700
Data Index: 8066008 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0165. Min Range: -6.0165
Max Act: 5.8602. Min Act: -0.1700
Data Index: 6544528 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0165. Min Range: -6.0165
Max Act: 5.8290. Min Act: -0.1700
Data Index: 5917026 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0165. Min Range: -6.0165
Max Act: 5.7977. Min Act: -0.1700
Data Index: 2734489 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0165. Min Range: -6.0165
Max Act: 5.7665. Min Act: -0.1700
Data Index: 1089680 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0165. Min Range: -6.0165
Max Act: 5.6727. Min Act: -0.1700
Data Index: 1002960 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0165. Min Range: -6.0165
Max Act: 5.6415. Min Act: -0.1700
Data Index: 5793012 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0165. Min Range: -6.0165
Max Act: 5.6415. Min Act: -0.1700
Data Index: 7591187 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0165. Min Range: -6.0165
Max Act: 5.5790. Min Act: -0.1700
Data Index: 7627431 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0165. Min Range: -6.0165
Max Act: 5.5790. Min Act: -0.1700
Data Index: 8090341 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0165. Min Range: -6.0165
Max Act: 5.5477. Min Act: -0.1700
Data Index: 459645 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0165. Min Range: -6.0165
Max Act: 5.5477. Min Act: -0.1700
Data Index: 1007596 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0165. Min Range: -6.0165
Max Act: 5.5165. Min Act: -0.1700
Data Index: 7064312 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0165. Min Range: -6.0165
Max Act: 5.5165. Min Act: -0.1700
Data Index: 4669079 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0165. Min Range: -6.0165
Max Act: 5.5165. Min Act: -0.1700
Data Index: 7634452 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0165. Min Range: -6.0165
Max Act: 5.5165. Min Act: -0.1700
Data Index: 1932747 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0165. Min Range: -6.0165
Max Act: 5.5165. Min Act: -0.1700
Data Index: 560561 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0165. Min Range: -6.0165
Max Act: 5.5165. Min Act: -0.1700
Data Index: 3457894 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19