Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6125 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1797. Min Range: -7.1797
Max Act: 7.1797. Min Act: -0.1700
Data Index: 3436180 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1797. Min Range: -7.1797
Max Act: 7.1172. Min Act: -0.1700
Data Index: 4261113 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1797. Min Range: -7.1797
Max Act: 7.1172. Min Act: -0.1700
Data Index: 1506409 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1797. Min Range: -7.1797
Max Act: 6.9609. Min Act: -0.1700
Data Index: 3213463 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1797. Min Range: -7.1797
Max Act: 6.9609. Min Act: -0.1700
Data Index: 8423367 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1797. Min Range: -7.1797
Max Act: 6.9297. Min Act: -0.1700
Data Index: 1621975 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1797. Min Range: -7.1797
Max Act: 6.9297. Min Act: -0.1700
Data Index: 7952493 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1797. Min Range: -7.1797
Max Act: 6.8672. Min Act: -0.1700
Data Index: 2014093 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1797. Min Range: -7.1797
Max Act: 6.8672. Min Act: -0.1700
Data Index: 1049049 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1797. Min Range: -7.1797
Max Act: 6.8359. Min Act: -0.1700
Data Index: 6298435 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1797. Min Range: -7.1797
Max Act: 6.8359. Min Act: -0.1700
Data Index: 6380445 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1797. Min Range: -7.1797
Max Act: 6.8359. Min Act: -0.1700
Data Index: 1188593 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1797. Min Range: -7.1797
Max Act: 6.8359. Min Act: -0.1700
Data Index: 5616862 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1797. Min Range: -7.1797
Max Act: 6.8047. Min Act: -0.1700
Data Index: 6317277 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1797. Min Range: -7.1797
Max Act: 6.8047. Min Act: -0.1700
Data Index: 2065286 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1797. Min Range: -7.1797
Max Act: 6.7734. Min Act: -0.1700
Data Index: 8146762 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1797. Min Range: -7.1797
Max Act: 6.7422. Min Act: -0.1700
Data Index: 7569296 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1797. Min Range: -7.1797
Max Act: 6.7734. Min Act: -0.1700
Data Index: 7063130 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1797. Min Range: -7.1797
Max Act: 6.7734. Min Act: -0.1700
Data Index: 6893918 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1797. Min Range: -7.1797
Max Act: 6.7422. Min Act: -0.1700
Data Index: 3348210 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19