Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3361 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7028. Min Range: -5.7028
Max Act: 5.7028. Min Act: -0.1700
Data Index: 6760335 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7028. Min Range: -5.7028
Max Act: 5.5778. Min Act: -0.1700
Data Index: 4992556 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7028. Min Range: -5.7028
Max Act: 5.5778. Min Act: -0.1700
Data Index: 3402532 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7028. Min Range: -5.7028
Max Act: 5.5778. Min Act: -0.1700
Data Index: 1254879 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7028. Min Range: -5.7028
Max Act: 5.5466. Min Act: -0.1700
Data Index: 8751217 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7028. Min Range: -5.7028
Max Act: 5.5153. Min Act: -0.1700
Data Index: 8317726 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7028. Min Range: -5.7028
Max Act: 5.5153. Min Act: -0.1700
Data Index: 5578607 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7028. Min Range: -5.7028
Max Act: 5.4841. Min Act: -0.1700
Data Index: 3402530 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7028. Min Range: -5.7028
Max Act: 5.4841. Min Act: -0.1700
Data Index: 3175683 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7028. Min Range: -5.7028
Max Act: 5.4841. Min Act: -0.1700
Data Index: 6676274 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7028. Min Range: -5.7028
Max Act: 5.4528. Min Act: -0.1700
Data Index: 2658487 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7028. Min Range: -5.7028
Max Act: 5.4528. Min Act: -0.1700
Data Index: 5274212 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7028. Min Range: -5.7028
Max Act: 5.4528. Min Act: -0.1700
Data Index: 6587842 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7028. Min Range: -5.7028
Max Act: 5.4216. Min Act: -0.1700
Data Index: 7659838 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7028. Min Range: -5.7028
Max Act: 5.4216. Min Act: -0.1700
Data Index: 4913817 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7028. Min Range: -5.7028
Max Act: 5.3903. Min Act: -0.1700
Data Index: 5540136 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7028. Min Range: -5.7028
Max Act: 5.3903. Min Act: -0.1700
Data Index: 4267748 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7028. Min Range: -5.7028
Max Act: 5.3903. Min Act: -0.1700
Data Index: 6444440 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7028. Min Range: -5.7028
Max Act: 5.3903. Min Act: -0.1700
Data Index: 7226630 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7028. Min Range: -5.7028
Max Act: 5.3903. Min Act: -0.1700
Data Index: 3965165 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19