Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 880 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8115. Min Range: -3.8115
Max Act: 3.8115. Min Act: -0.1700
Data Index: 6200229 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8115. Min Range: -3.8115
Max Act: 3.8115. Min Act: -0.1700
Data Index: 5458981 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8115. Min Range: -3.8115
Max Act: 3.8115. Min Act: -0.1700
Data Index: 8232900 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8115. Min Range: -3.8115
Max Act: 3.8115. Min Act: -0.1700
Data Index: 4353608 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8115. Min Range: -3.8115
Max Act: 3.8115. Min Act: -0.1700
Data Index: 5724335 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8115. Min Range: -3.8115
Max Act: 3.8115. Min Act: -0.1700
Data Index: 8189797 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8115. Min Range: -3.8115
Max Act: 3.8115. Min Act: -0.1700
Data Index: 1057547 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8115. Min Range: -3.8115
Max Act: 3.8115. Min Act: -0.1700
Data Index: 4353261 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8115. Min Range: -3.8115
Max Act: 3.8115. Min Act: -0.1700
Data Index: 4266898 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8115. Min Range: -3.8115
Max Act: 3.8115. Min Act: -0.1700
Data Index: 1008369 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8115. Min Range: -3.8115
Max Act: 3.8115. Min Act: -0.1700
Data Index: 2066313 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8115. Min Range: -3.8115
Max Act: 3.8115. Min Act: -0.1700
Data Index: 856392 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8115. Min Range: -3.8115
Max Act: 3.8115. Min Act: -0.1700
Data Index: 1291579 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8115. Min Range: -3.8115
Max Act: 3.8115. Min Act: -0.1700
Data Index: 3566464 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8115. Min Range: -3.8115
Max Act: 3.8115. Min Act: -0.1700
Data Index: 3300144 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8115. Min Range: -3.8115
Max Act: 3.8115. Min Act: -0.1700
Data Index: 5459637 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8115. Min Range: -3.8115
Max Act: 3.8115. Min Act: -0.1700
Data Index: 5729607 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8115. Min Range: -3.8115
Max Act: 3.8115. Min Act: -0.1700
Data Index: 2185529 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8115. Min Range: -3.8115
Max Act: 3.8115. Min Act: -0.1700
Data Index: 1406 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8115. Min Range: -3.8115
Max Act: 3.8115. Min Act: -0.1700
Data Index: 7095280 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19