Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4504 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.4679. Min Act: -0.1700
Data Index: 6174466 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.4054. Min Act: -0.1700
Data Index: 5785559 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.4054. Min Act: -0.1700
Data Index: 4843709 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.3742. Min Act: -0.1700
Data Index: 953054 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.3742. Min Act: -0.1700
Data Index: 8345259 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.3742. Min Act: -0.1700
Data Index: 4843707 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.3742. Min Act: -0.1700
Data Index: 3629537 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.3742. Min Act: -0.1700
Data Index: 8408741 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.3742. Min Act: -0.1700
Data Index: 7724007 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.3429. Min Act: -0.1700
Data Index: 6355298 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.3429. Min Act: -0.1700
Data Index: 2198089 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.3429. Min Act: -0.1700
Data Index: 3048010 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.3117. Min Act: -0.1700
Data Index: 7817732 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.3429. Min Act: -0.1700
Data Index: 2041684 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.3429. Min Act: -0.1700
Data Index: 7323101 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.3429. Min Act: -0.1699
Data Index: 6523245 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.3429. Min Act: -0.1700
Data Index: 1196005 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.3117. Min Act: -0.1700
Data Index: 5633772 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.3429. Min Act: -0.1700
Data Index: 5608506 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.3429. Min Act: -0.1700
Data Index: 4983923 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19