Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4550 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5851. Min Range: -6.5851
Max Act: 6.5851. Min Act: -0.1700
Data Index: 7896217 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5851. Min Range: -6.5851
Max Act: 6.5539. Min Act: -0.1700
Data Index: 8618163 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5851. Min Range: -6.5851
Max Act: 6.3664. Min Act: -0.1700
Data Index: 5823272 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5851. Min Range: -6.5851
Max Act: 6.3664. Min Act: -0.1700
Data Index: 2161846 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5851. Min Range: -6.5851
Max Act: 6.3351. Min Act: -0.1700
Data Index: 2969635 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5851. Min Range: -6.5851
Max Act: 6.3351. Min Act: -0.1700
Data Index: 1180713 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5851. Min Range: -6.5851
Max Act: 6.3351. Min Act: -0.1700
Data Index: 91752 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5851. Min Range: -6.5851
Max Act: 6.3351. Min Act: -0.1700
Data Index: 214885 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5851. Min Range: -6.5851
Max Act: 6.3039. Min Act: -0.1700
Data Index: 2829943 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5851. Min Range: -6.5851
Max Act: 6.2726. Min Act: -0.1700
Data Index: 6203568 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5851. Min Range: -6.5851
Max Act: 6.2726. Min Act: -0.1700
Data Index: 7469358 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5851. Min Range: -6.5851
Max Act: 6.2414. Min Act: -0.1700
Data Index: 2744202 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5851. Min Range: -6.5851
Max Act: 6.2414. Min Act: -0.1700
Data Index: 1473308 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5851. Min Range: -6.5851
Max Act: 6.2101. Min Act: -0.1700
Data Index: 4586223 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5851. Min Range: -6.5851
Max Act: 6.1789. Min Act: -0.1700
Data Index: 4869578 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5851. Min Range: -6.5851
Max Act: 6.1476. Min Act: -0.1700
Data Index: 6098166 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5851. Min Range: -6.5851
Max Act: 6.1476. Min Act: -0.1700
Data Index: 7378637 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5851. Min Range: -6.5851
Max Act: 6.1476. Min Act: -0.1700
Data Index: 8395262 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5851. Min Range: -6.5851
Max Act: 6.1476. Min Act: -0.1700
Data Index: 3413796 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5851. Min Range: -6.5851
Max Act: 6.1476. Min Act: -0.1700
Data Index: 6220613 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19