Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4322 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2634. Min Range: -6.2634
Max Act: 6.2634. Min Act: -0.1700
Data Index: 5622090 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2634. Min Range: -6.2634
Max Act: 6.2634. Min Act: -0.1700
Data Index: 3154000 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2634. Min Range: -6.2634
Max Act: 6.2009. Min Act: -0.1700
Data Index: 6928800 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2634. Min Range: -6.2634
Max Act: 6.1697. Min Act: -0.1700
Data Index: 6955224 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2634. Min Range: -6.2634
Max Act: 6.1384. Min Act: -0.1700
Data Index: 4909681 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2634. Min Range: -6.2634
Max Act: 6.1072. Min Act: -0.1700
Data Index: 4762019 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2634. Min Range: -6.2634
Max Act: 6.1384. Min Act: -0.1700
Data Index: 5947948 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2634. Min Range: -6.2634
Max Act: 6.1072. Min Act: -0.1700
Data Index: 2451310 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2634. Min Range: -6.2634
Max Act: 6.1072. Min Act: -0.1700
Data Index: 3351117 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2634. Min Range: -6.2634
Max Act: 6.0759. Min Act: -0.1700
Data Index: 6792304 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2634. Min Range: -6.2634
Max Act: 6.0759. Min Act: -0.1700
Data Index: 6034646 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2634. Min Range: -6.2634
Max Act: 6.0759. Min Act: -0.1700
Data Index: 2446252 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2634. Min Range: -6.2634
Max Act: 6.0759. Min Act: -0.1700
Data Index: 4572860 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2634. Min Range: -6.2634
Max Act: 6.0447. Min Act: -0.1700
Data Index: 6034644 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2634. Min Range: -6.2634
Max Act: 6.0447. Min Act: -0.1700
Data Index: 8297586 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2634. Min Range: -6.2634
Max Act: 6.0134. Min Act: -0.1700
Data Index: 94905 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2634. Min Range: -6.2634
Max Act: 5.9822. Min Act: -0.1700
Data Index: 6034645 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2634. Min Range: -6.2634
Max Act: 5.9822. Min Act: -0.1700
Data Index: 3667377 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2634. Min Range: -6.2634
Max Act: 5.9822. Min Act: -0.1700
Data Index: 7893537 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2634. Min Range: -6.2634
Max Act: 5.9822. Min Act: -0.1700
Data Index: 4094156 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19