Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5942 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4745. Min Range: -10.4745
Max Act: 10.4745. Min Act: -0.1700
Data Index: 4390751 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4745. Min Range: -10.4745
Max Act: 9.9120. Min Act: -0.1700
Data Index: 2508761 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4745. Min Range: -10.4745
Max Act: 9.7870. Min Act: -0.1700
Data Index: 7668863 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4745. Min Range: -10.4745
Max Act: 9.7870. Min Act: -0.1700
Data Index: 689322 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4745. Min Range: -10.4745
Max Act: 9.7245. Min Act: -0.1700
Data Index: 6366338 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4745. Min Range: -10.4745
Max Act: 9.6620. Min Act: -0.1700
Data Index: 5004535 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4745. Min Range: -10.4745
Max Act: 9.5995. Min Act: -0.1700
Data Index: 122128 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4745. Min Range: -10.4745
Max Act: 9.5995. Min Act: -0.1700
Data Index: 6598074 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4745. Min Range: -10.4745
Max Act: 9.5370. Min Act: -0.1700
Data Index: 6836213 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4745. Min Range: -10.4745
Max Act: 9.5370. Min Act: -0.1700
Data Index: 4769154 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4745. Min Range: -10.4745
Max Act: 9.5370. Min Act: -0.1700
Data Index: 6708494 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4745. Min Range: -10.4745
Max Act: 9.5370. Min Act: -0.1700
Data Index: 556524 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4745. Min Range: -10.4745
Max Act: 9.5370. Min Act: -0.1700
Data Index: 1139878 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4745. Min Range: -10.4745
Max Act: 9.5370. Min Act: -0.1700
Data Index: 6567595 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4745. Min Range: -10.4745
Max Act: 9.4745. Min Act: -0.1700
Data Index: 4057043 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4745. Min Range: -10.4745
Max Act: 9.5370. Min Act: -0.1700
Data Index: 5328275 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4745. Min Range: -10.4745
Max Act: 9.4745. Min Act: -0.1700
Data Index: 6955083 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4745. Min Range: -10.4745
Max Act: 9.5370. Min Act: -0.1700
Data Index: 6387279 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4745. Min Range: -10.4745
Max Act: 9.4120. Min Act: -0.1700
Data Index: 3888138 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4745. Min Range: -10.4745
Max Act: 9.4120. Min Act: -0.1700
Data Index: 1446587 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19