Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3537 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0926. Min Range: -5.0926
Max Act: 5.0926. Min Act: -0.1700
Data Index: 6126413 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0926. Min Range: -5.0926
Max Act: 5.0301. Min Act: -0.1700
Data Index: 3133691 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0926. Min Range: -5.0926
Max Act: 4.9989. Min Act: -0.1700
Data Index: 8042544 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0926. Min Range: -5.0926
Max Act: 4.9364. Min Act: -0.1700
Data Index: 8810083 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0926. Min Range: -5.0926
Max Act: 4.9051. Min Act: -0.1700
Data Index: 6224592 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0926. Min Range: -5.0926
Max Act: 4.8739. Min Act: -0.1700
Data Index: 8269392 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0926. Min Range: -5.0926
Max Act: 4.8739. Min Act: -0.1700
Data Index: 787176 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0926. Min Range: -5.0926
Max Act: 4.8739. Min Act: -0.1700
Data Index: 5414033 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0926. Min Range: -5.0926
Max Act: 4.8739. Min Act: -0.1700
Data Index: 6854464 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0926. Min Range: -5.0926
Max Act: 4.8739. Min Act: -0.1700
Data Index: 1972182 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0926. Min Range: -5.0926
Max Act: 4.8739. Min Act: -0.1700
Data Index: 132375 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0926. Min Range: -5.0926
Max Act: 4.8739. Min Act: -0.1700
Data Index: 689729 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0926. Min Range: -5.0926
Max Act: 4.8739. Min Act: -0.1700
Data Index: 7655664 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0926. Min Range: -5.0926
Max Act: 4.8739. Min Act: -0.1700
Data Index: 5529743 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0926. Min Range: -5.0926
Max Act: 4.9051. Min Act: -0.1700
Data Index: 4005125 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0926. Min Range: -5.0926
Max Act: 4.8426. Min Act: -0.1700
Data Index: 5143464 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0926. Min Range: -5.0926
Max Act: 4.8739. Min Act: -0.1700
Data Index: 8119868 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0926. Min Range: -5.0926
Max Act: 4.8114. Min Act: -0.1700
Data Index: 7623841 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0926. Min Range: -5.0926
Max Act: 4.8114. Min Act: -0.1700
Data Index: 1709917 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0926. Min Range: -5.0926
Max Act: 4.8426. Min Act: -0.1700
Data Index: 2604882 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19