Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3518 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3828. Min Range: -7.3828
Max Act: 7.3828. Min Act: -0.1700
Data Index: 5369742 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3828. Min Range: -7.3828
Max Act: 7.3516. Min Act: -0.1700
Data Index: 1226816 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3828. Min Range: -7.3828
Max Act: 7.1953. Min Act: -0.1700
Data Index: 1021952 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3828. Min Range: -7.3828
Max Act: 7.1328. Min Act: -0.1700
Data Index: 4332967 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3828. Min Range: -7.3828
Max Act: 7.1328. Min Act: -0.1700
Data Index: 3831822 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3828. Min Range: -7.3828
Max Act: 7.1016. Min Act: -0.1700
Data Index: 5003192 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3828. Min Range: -7.3828
Max Act: 7.1016. Min Act: -0.1700
Data Index: 7020023 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3828. Min Range: -7.3828
Max Act: 7.1016. Min Act: -0.1700
Data Index: 3857694 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3828. Min Range: -7.3828
Max Act: 6.9766. Min Act: -0.1700
Data Index: 2881303 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3828. Min Range: -7.3828
Max Act: 6.9766. Min Act: -0.1700
Data Index: 1483476 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3828. Min Range: -7.3828
Max Act: 6.9453. Min Act: -0.1700
Data Index: 640747 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3828. Min Range: -7.3828
Max Act: 6.9141. Min Act: -0.1700
Data Index: 8018683 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3828. Min Range: -7.3828
Max Act: 6.8828. Min Act: -0.1700
Data Index: 7394701 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3828. Min Range: -7.3828
Max Act: 6.8828. Min Act: -0.1700
Data Index: 2203229 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3828. Min Range: -7.3828
Max Act: 6.8516. Min Act: -0.1700
Data Index: 5103710 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3828. Min Range: -7.3828
Max Act: 6.8516. Min Act: -0.1700
Data Index: 2158654 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3828. Min Range: -7.3828
Max Act: 6.8828. Min Act: -0.1700
Data Index: 3434333 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3828. Min Range: -7.3828
Max Act: 6.8203. Min Act: -0.1700
Data Index: 3386082 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3828. Min Range: -7.3828
Max Act: 6.8516. Min Act: -0.1700
Data Index: 8359606 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3828. Min Range: -7.3828
Max Act: 6.7578. Min Act: -0.1700
Data Index: 7796687 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19