Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3870 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2986. Min Range: -3.2986
Max Act: 3.2986. Min Act: -0.1700
Data Index: 44998 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2986. Min Range: -3.2986
Max Act: 3.1886. Min Act: -0.1700
Data Index: 1447763 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2986. Min Range: -3.2986
Max Act: 3.1729. Min Act: -0.1700
Data Index: 1195485 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2986. Min Range: -3.2986
Max Act: 2.8886. Min Act: -0.1700
Data Index: 1550022 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2986. Min Range: -3.2986
Max Act: 2.8886. Min Act: -0.1700
Data Index: 7403634 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2986. Min Range: -3.2986
Max Act: 2.8728. Min Act: -0.1700
Data Index: 3714261 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2986. Min Range: -3.2986
Max Act: 2.8569. Min Act: -0.1700
Data Index: 7029569 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2986. Min Range: -3.2986
Max Act: 2.8251. Min Act: -0.1700
Data Index: 7366500 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2986. Min Range: -3.2986
Max Act: 2.8410. Min Act: -0.1700
Data Index: 6874235 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2986. Min Range: -3.2986
Max Act: 2.8092. Min Act: -0.1700
Data Index: 3102612 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2986. Min Range: -3.2986
Max Act: 2.8092. Min Act: -0.1700
Data Index: 3184623 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2986. Min Range: -3.2986
Max Act: 2.8251. Min Act: -0.1700
Data Index: 1141853 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2986. Min Range: -3.2986
Max Act: 2.7773. Min Act: -0.1700
Data Index: 6354693 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2986. Min Range: -3.2986
Max Act: 2.7933. Min Act: -0.1700
Data Index: 3099683 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2986. Min Range: -3.2986
Max Act: 2.7454. Min Act: -0.1700
Data Index: 6772683 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2986. Min Range: -3.2986
Max Act: 2.7294. Min Act: -0.1700
Data Index: 5753329 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2986. Min Range: -3.2986
Max Act: 2.6975. Min Act: -0.1700
Data Index: 1648414 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2986. Min Range: -3.2986
Max Act: 2.7294. Min Act: -0.1700
Data Index: 2242012 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2986. Min Range: -3.2986
Max Act: 2.7294. Min Act: -0.1700
Data Index: 4381074 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2986. Min Range: -3.2986
Max Act: 2.7135. Min Act: -0.1700
Data Index: 5119010 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19