Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5462 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9681. Min Range: -6.9681
Max Act: 6.9681. Min Act: -0.1700
Data Index: 4366599 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9681. Min Range: -6.9681
Max Act: 6.8431. Min Act: -0.1700
Data Index: 5960206 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9681. Min Range: -6.9681
Max Act: 6.6868. Min Act: -0.1700
Data Index: 6526315 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9681. Min Range: -6.9681
Max Act: 6.6243. Min Act: -0.1700
Data Index: 6761692 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9681. Min Range: -6.9681
Max Act: 6.6243. Min Act: -0.1700
Data Index: 6535864 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9681. Min Range: -6.9681
Max Act: 6.5931. Min Act: -0.1700
Data Index: 7333839 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9681. Min Range: -6.9681
Max Act: 6.5618. Min Act: -0.1700
Data Index: 8206188 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9681. Min Range: -6.9681
Max Act: 6.5931. Min Act: -0.1700
Data Index: 3639323 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9681. Min Range: -6.9681
Max Act: 6.5618. Min Act: -0.1700
Data Index: 7841567 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9681. Min Range: -6.9681
Max Act: 6.5618. Min Act: -0.1700
Data Index: 1797052 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9681. Min Range: -6.9681
Max Act: 6.5306. Min Act: -0.1700
Data Index: 5649972 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9681. Min Range: -6.9681
Max Act: 6.5306. Min Act: -0.1700
Data Index: 5430376 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9681. Min Range: -6.9681
Max Act: 6.4993. Min Act: -0.1700
Data Index: 5725891 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9681. Min Range: -6.9681
Max Act: 6.4993. Min Act: -0.1700
Data Index: 4248442 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9681. Min Range: -6.9681
Max Act: 6.4993. Min Act: -0.1700
Data Index: 6535865 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9681. Min Range: -6.9681
Max Act: 6.4993. Min Act: -0.1700
Data Index: 7860814 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9681. Min Range: -6.9681
Max Act: 6.4993. Min Act: -0.1700
Data Index: 111556 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9681. Min Range: -6.9681
Max Act: 6.4681. Min Act: -0.1700
Data Index: 3937555 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9681. Min Range: -6.9681
Max Act: 6.4681. Min Act: -0.1700
Data Index: 4678927 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9681. Min Range: -6.9681
Max Act: 6.4681. Min Act: -0.1700
Data Index: 1595167 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19