Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3311 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6849. Min Range: -3.6849
Max Act: 3.6536. Min Act: -0.1700
Data Index: 8658000 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6849. Min Range: -3.6849
Max Act: 3.6849. Min Act: -0.1700
Data Index: 8380309 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6849. Min Range: -3.6849
Max Act: 3.6536. Min Act: -0.1700
Data Index: 8098469 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6849. Min Range: -3.6849
Max Act: 3.6536. Min Act: -0.1700
Data Index: 7665362 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6849. Min Range: -3.6849
Max Act: 3.6536. Min Act: -0.1700
Data Index: 7250241 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6849. Min Range: -3.6849
Max Act: 3.6536. Min Act: -0.1700
Data Index: 6864516 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6849. Min Range: -3.6849
Max Act: 3.6536. Min Act: -0.1700
Data Index: 1590489 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6849. Min Range: -3.6849
Max Act: 3.6536. Min Act: -0.1700
Data Index: 5995971 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6849. Min Range: -3.6849
Max Act: 3.6536. Min Act: -0.1700
Data Index: 1561635 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6849. Min Range: -3.6849
Max Act: 3.6536. Min Act: -0.1700
Data Index: 5987351 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6849. Min Range: -3.6849
Max Act: 3.6536. Min Act: -0.1700
Data Index: 5789831 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6849. Min Range: -3.6849
Max Act: 3.6536. Min Act: -0.1700
Data Index: 1281913 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6849. Min Range: -3.6849
Max Act: 3.6536. Min Act: -0.1700
Data Index: 462144 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6849. Min Range: -3.6849
Max Act: 3.6536. Min Act: -0.1700
Data Index: 5238214 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6849. Min Range: -3.6849
Max Act: 3.6536. Min Act: -0.1700
Data Index: 5021571 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6849. Min Range: -3.6849
Max Act: 3.6536. Min Act: -0.1700
Data Index: 1021103 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6849. Min Range: -3.6849
Max Act: 3.6536. Min Act: -0.1700
Data Index: 4420123 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6849. Min Range: -3.6849
Max Act: 3.6536. Min Act: -0.1700
Data Index: 4130720 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6849. Min Range: -3.6849
Max Act: 3.6536. Min Act: -0.1700
Data Index: 838821 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6849. Min Range: -3.6849
Max Act: 3.6536. Min Act: -0.1700
Data Index: 4128954 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19