Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6273 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.8587. Min Range: -13.8587
Max Act: 13.8587. Min Act: -0.1700
Data Index: 5151605 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.8587. Min Range: -13.8587
Max Act: 13.7337. Min Act: -0.1700
Data Index: 5151608 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.8587. Min Range: -13.8587
Max Act: 13.4212. Min Act: -0.1700
Data Index: 6236798 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.8587. Min Range: -13.8587
Max Act: 13.1712. Min Act: -0.1700
Data Index: 3483652 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.8587. Min Range: -13.8587
Max Act: 12.9212. Min Act: -0.1700
Data Index: 3744497 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.8587. Min Range: -13.8587
Max Act: 12.8587. Min Act: -0.1700
Data Index: 7868703 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.8587. Min Range: -13.8587
Max Act: 12.7337. Min Act: -0.1700
Data Index: 2237966 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.8587. Min Range: -13.8587
Max Act: 12.7337. Min Act: -0.1700
Data Index: 3732251 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.8587. Min Range: -13.8587
Max Act: 12.6712. Min Act: -0.1700
Data Index: 8822591 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.8587. Min Range: -13.8587
Max Act: 12.6712. Min Act: -0.1700
Data Index: 893585 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.8587. Min Range: -13.8587
Max Act: 12.6712. Min Act: -0.1700
Data Index: 7465535 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.8587. Min Range: -13.8587
Max Act: 12.6712. Min Act: -0.1700
Data Index: 7069692 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.8587. Min Range: -13.8587
Max Act: 12.6087. Min Act: -0.1700
Data Index: 5900389 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.8587. Min Range: -13.8587
Max Act: 12.6087. Min Act: -0.1700
Data Index: 5474832 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.8587. Min Range: -13.8587
Max Act: 12.5462. Min Act: -0.1700
Data Index: 5715333 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.8587. Min Range: -13.8587
Max Act: 12.5462. Min Act: -0.1700
Data Index: 4065394 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.8587. Min Range: -13.8587
Max Act: 12.4837. Min Act: -0.1700
Data Index: 5474806 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.8587. Min Range: -13.8587
Max Act: 12.4212. Min Act: -0.1700
Data Index: 877947 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.8587. Min Range: -13.8587
Max Act: 12.4212. Min Act: -0.1700
Data Index: 5474823 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.8587. Min Range: -13.8587
Max Act: 12.4212. Min Act: -0.1700
Data Index: 1882033 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19