Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3428 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7859. Min Range: -1.7859
Max Act: 1.7859. Min Act: -0.1700
Data Index: 7405103 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7859. Min Range: -1.7859
Max Act: 1.7600. Min Act: -0.1700
Data Index: 7171706 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7859. Min Range: -1.7859
Max Act: 1.7341. Min Act: -0.1700
Data Index: 6581062 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7859. Min Range: -1.7859
Max Act: 1.7427. Min Act: -0.1700
Data Index: 4713983 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7859. Min Range: -1.7859
Max Act: 1.7427. Min Act: -0.1697
Data Index: 976183 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7859. Min Range: -1.7859
Max Act: 1.7427. Min Act: -0.1688
Data Index: 4609262 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7859. Min Range: -1.7859
Max Act: 1.7427. Min Act: -0.1659
Data Index: 7122060 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7859. Min Range: -1.7859
Max Act: 1.7427. Min Act: -0.1700
Data Index: 7740401 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7859. Min Range: -1.7859
Max Act: 1.7341. Min Act: -0.1689
Data Index: 2994787 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7859. Min Range: -1.7859
Max Act: 1.7168. Min Act: -0.1700
Data Index: 1690909 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7859. Min Range: -1.7859
Max Act: 1.7168. Min Act: -0.1699
Data Index: 19548 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7859. Min Range: -1.7859
Max Act: 1.7081. Min Act: -0.1697
Data Index: 865527 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7859. Min Range: -1.7859
Max Act: 1.6995. Min Act: -0.1700
Data Index: 7075862 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7859. Min Range: -1.7859
Max Act: 1.6908. Min Act: -0.1700
Data Index: 7286868 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7859. Min Range: -1.7859
Max Act: 1.6908. Min Act: -0.1696
Data Index: 5216336 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7859. Min Range: -1.7859
Max Act: 1.6908. Min Act: -0.1699
Data Index: 1874710 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7859. Min Range: -1.7859
Max Act: 1.6821. Min Act: -0.1700
Data Index: 383737 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7859. Min Range: -1.7859
Max Act: 1.6821. Min Act: -0.1699
Data Index: 4139854 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7859. Min Range: -1.7859
Max Act: 1.6821. Min Act: -0.1700
Data Index: 3528102 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7859. Min Range: -1.7859
Max Act: 1.6647. Min Act: -0.1688
Data Index: 4616937 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19