Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2983 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0745. Min Range: -7.0745
Max Act: 7.0745. Min Act: -0.1700
Data Index: 8373905 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.9495. Min Act: -0.1700
Data Index: 8373910 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.8245. Min Act: -0.1700
Data Index: 8373917 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.8245. Min Act: -0.1700
Data Index: 8373906 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.7620. Min Act: -0.1700
Data Index: 8373900 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.7620. Min Act: -0.1700
Data Index: 8373916 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.7620. Min Act: -0.1700
Data Index: 8373912 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.7620. Min Act: -0.1700
Data Index: 8373913 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.6995. Min Act: -0.1700
Data Index: 8626858 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.6995. Min Act: -0.1700
Data Index: 2506111 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.6995. Min Act: -0.1700
Data Index: 1218903 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.6683. Min Act: -0.1698
Data Index: 8626859 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.6370. Min Act: -0.1700
Data Index: 8373904 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.6058. Min Act: -0.1700
Data Index: 8373919 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.5745. Min Act: -0.1700
Data Index: 8373918 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.5745. Min Act: -0.1700
Data Index: 8373915 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.5120. Min Act: -0.1700
Data Index: 8373901 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.5120. Min Act: -0.1700
Data Index: 1218905 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.4808. Min Act: -0.1700
Data Index: 1218902 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0745. Min Range: -7.0745
Max Act: 6.5120. Min Act: -0.1700
Data Index: 8373907 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19