Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2826 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9137. Min Range: -5.9137
Max Act: 5.9137. Min Act: -0.1700
Data Index: 5467234 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9137. Min Range: -5.9137
Max Act: 5.8825. Min Act: -0.1700
Data Index: 2987576 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9137. Min Range: -5.9137
Max Act: 5.8825. Min Act: -0.1700
Data Index: 6349147 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9137. Min Range: -5.9137
Max Act: 5.8512. Min Act: -0.1700
Data Index: 7105006 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9137. Min Range: -5.9137
Max Act: 5.8512. Min Act: -0.1700
Data Index: 8120279 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9137. Min Range: -5.9137
Max Act: 5.8200. Min Act: -0.1700
Data Index: 3067882 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9137. Min Range: -5.9137
Max Act: 5.8200. Min Act: -0.1700
Data Index: 5417161 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9137. Min Range: -5.9137
Max Act: 5.7887. Min Act: -0.1700
Data Index: 231860 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9137. Min Range: -5.9137
Max Act: 5.7575. Min Act: -0.1700
Data Index: 6106412 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9137. Min Range: -5.9137
Max Act: 5.7262. Min Act: -0.1700
Data Index: 5139616 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9137. Min Range: -5.9137
Max Act: 5.6950. Min Act: -0.1700
Data Index: 1445089 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9137. Min Range: -5.9137
Max Act: 5.6950. Min Act: -0.1700
Data Index: 1804449 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9137. Min Range: -5.9137
Max Act: 5.6950. Min Act: -0.1700
Data Index: 514848 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9137. Min Range: -5.9137
Max Act: 5.6950. Min Act: -0.1700
Data Index: 6096335 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9137. Min Range: -5.9137
Max Act: 5.6637. Min Act: -0.1700
Data Index: 3512533 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9137. Min Range: -5.9137
Max Act: 5.6325. Min Act: -0.1700
Data Index: 6256364 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9137. Min Range: -5.9137
Max Act: 5.6012. Min Act: -0.1700
Data Index: 5220872 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9137. Min Range: -5.9137
Max Act: 5.6012. Min Act: -0.1700
Data Index: 6484679 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9137. Min Range: -5.9137
Max Act: 5.4762. Min Act: -0.1700
Data Index: 5220871 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9137. Min Range: -5.9137
Max Act: 5.4450. Min Act: -0.1700
Data Index: 2135633 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19