Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3165 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8697. Min Range: -8.8697
Max Act: 8.8697. Min Act: -0.1700
Data Index: 2167974 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8697. Min Range: -8.8697
Max Act: 8.5572. Min Act: -0.1700
Data Index: 8023254 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8697. Min Range: -8.8697
Max Act: 8.5572. Min Act: -0.1700
Data Index: 4278145 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8697. Min Range: -8.8697
Max Act: 8.4947. Min Act: -0.1700
Data Index: 8460665 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8697. Min Range: -8.8697
Max Act: 8.4947. Min Act: -0.1700
Data Index: 5813800 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8697. Min Range: -8.8697
Max Act: 8.4947. Min Act: -0.1700
Data Index: 7389550 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8697. Min Range: -8.8697
Max Act: 8.4322. Min Act: -0.1700
Data Index: 66651 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8697. Min Range: -8.8697
Max Act: 8.4322. Min Act: -0.1700
Data Index: 647680 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8697. Min Range: -8.8697
Max Act: 8.3072. Min Act: -0.1700
Data Index: 1216242 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8697. Min Range: -8.8697
Max Act: 8.3697. Min Act: -0.1700
Data Index: 4674969 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8697. Min Range: -8.8697
Max Act: 8.3072. Min Act: -0.1700
Data Index: 7430688 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8697. Min Range: -8.8697
Max Act: 8.3072. Min Act: -0.1700
Data Index: 7392697 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8697. Min Range: -8.8697
Max Act: 8.2447. Min Act: -0.1700
Data Index: 5923857 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8697. Min Range: -8.8697
Max Act: 8.2447. Min Act: -0.1700
Data Index: 4035748 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8697. Min Range: -8.8697
Max Act: 8.2447. Min Act: -0.1700
Data Index: 6738819 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8697. Min Range: -8.8697
Max Act: 8.1822. Min Act: -0.1700
Data Index: 5606066 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8697. Min Range: -8.8697
Max Act: 8.1822. Min Act: -0.1700
Data Index: 1053790 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8697. Min Range: -8.8697
Max Act: 8.1822. Min Act: -0.1700
Data Index: 8087117 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8697. Min Range: -8.8697
Max Act: 8.1822. Min Act: -0.1700
Data Index: 4383980 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8697. Min Range: -8.8697
Max Act: 8.1822. Min Act: -0.1700
Data Index: 4746424 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19