Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3825 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5980. Min Range: -8.5980
Max Act: 8.5980. Min Act: -0.1700
Data Index: 7242329 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5980. Min Range: -8.5980
Max Act: 8.5355. Min Act: -0.1700
Data Index: 7783302 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5980. Min Range: -8.5980
Max Act: 8.4730. Min Act: -0.1700
Data Index: 1288284 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5980. Min Range: -8.5980
Max Act: 8.4730. Min Act: -0.1700
Data Index: 7073844 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5980. Min Range: -8.5980
Max Act: 8.4730. Min Act: -0.1700
Data Index: 4363973 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5980. Min Range: -8.5980
Max Act: 8.4105. Min Act: -0.1700
Data Index: 3815214 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5980. Min Range: -8.5980
Max Act: 8.4105. Min Act: -0.1700
Data Index: 4166493 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5980. Min Range: -8.5980
Max Act: 8.4105. Min Act: -0.1700
Data Index: 2013727 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5980. Min Range: -8.5980
Max Act: 8.4105. Min Act: -0.1700
Data Index: 989620 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5980. Min Range: -8.5980
Max Act: 8.3480. Min Act: -0.1700
Data Index: 6564466 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5980. Min Range: -8.5980
Max Act: 8.2855. Min Act: -0.1700
Data Index: 4950136 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5980. Min Range: -8.5980
Max Act: 8.2855. Min Act: -0.1700
Data Index: 5533319 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5980. Min Range: -8.5980
Max Act: 8.2855. Min Act: -0.1700
Data Index: 4573085 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5980. Min Range: -8.5980
Max Act: 8.2855. Min Act: -0.1700
Data Index: 3842706 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5980. Min Range: -8.5980
Max Act: 8.2855. Min Act: -0.1700
Data Index: 3842699 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5980. Min Range: -8.5980
Max Act: 8.2855. Min Act: -0.1700
Data Index: 2873663 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5980. Min Range: -8.5980
Max Act: 8.2230. Min Act: -0.1700
Data Index: 4570729 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5980. Min Range: -8.5980
Max Act: 8.2230. Min Act: -0.1700
Data Index: 6691794 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5980. Min Range: -8.5980
Max Act: 8.2230. Min Act: -0.1700
Data Index: 5533301 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5980. Min Range: -8.5980
Max Act: 8.2230. Min Act: -0.1700
Data Index: 1396585 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19