Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3903 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9014. Min Range: -6.9014
Max Act: 6.8702. Min Act: -0.1700
Data Index: 4980747 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9014. Min Range: -6.9014
Max Act: 6.9014. Min Act: -0.1700
Data Index: 3285879 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9014. Min Range: -6.9014
Max Act: 6.7139. Min Act: -0.1700
Data Index: 7232623 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9014. Min Range: -6.9014
Max Act: 6.7139. Min Act: -0.1700
Data Index: 4906797 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9014. Min Range: -6.9014
Max Act: 6.6827. Min Act: -0.1700
Data Index: 3496934 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9014. Min Range: -6.9014
Max Act: 6.6514. Min Act: -0.1700
Data Index: 797823 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9014. Min Range: -6.9014
Max Act: 6.6514. Min Act: -0.1700
Data Index: 2881795 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9014. Min Range: -6.9014
Max Act: 6.6514. Min Act: -0.1700
Data Index: 3901628 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9014. Min Range: -6.9014
Max Act: 6.5889. Min Act: -0.1700
Data Index: 2977588 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9014. Min Range: -6.9014
Max Act: 6.5577. Min Act: -0.1700
Data Index: 2438179 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9014. Min Range: -6.9014
Max Act: 6.5577. Min Act: -0.1700
Data Index: 4269363 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9014. Min Range: -6.9014
Max Act: 6.5264. Min Act: -0.1700
Data Index: 8426160 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9014. Min Range: -6.9014
Max Act: 6.4952. Min Act: -0.1700
Data Index: 8458452 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9014. Min Range: -6.9014
Max Act: 6.4327. Min Act: -0.1700
Data Index: 1334903 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9014. Min Range: -6.9014
Max Act: 6.4952. Min Act: -0.1700
Data Index: 5508732 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9014. Min Range: -6.9014
Max Act: 6.4327. Min Act: -0.1700
Data Index: 1644580 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9014. Min Range: -6.9014
Max Act: 6.4014. Min Act: -0.1700
Data Index: 6186527 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9014. Min Range: -6.9014
Max Act: 6.4014. Min Act: -0.1700
Data Index: 1769065 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9014. Min Range: -6.9014
Max Act: 6.4014. Min Act: -0.1700
Data Index: 3843585 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9014. Min Range: -6.9014
Max Act: 6.4014. Min Act: -0.1700
Data Index: 876553 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19