Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1162 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.9704. Min Act: -0.1700
Data Index: 2174968 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.8767. Min Act: -0.1700
Data Index: 6759601 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.8142. Min Act: -0.1700
Data Index: 6297555 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.8142. Min Act: -0.1700
Data Index: 6149832 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.7829. Min Act: -0.1700
Data Index: 8444778 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.7517. Min Act: -0.1700
Data Index: 6513900 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.7517. Min Act: -0.1700
Data Index: 5583324 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.7204. Min Act: -0.1700
Data Index: 2736344 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.6579. Min Act: -0.1700
Data Index: 6555165 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.6579. Min Act: -0.1700
Data Index: 4985617 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.6579. Min Act: -0.1700
Data Index: 7933035 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.6267. Min Act: -0.1700
Data Index: 2130458 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.6267. Min Act: -0.1700
Data Index: 8444665 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.5954. Min Act: -0.1700
Data Index: 6150568 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.5642. Min Act: -0.1700
Data Index: 675210 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.5329. Min Act: -0.1700
Data Index: 964813 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.5329. Min Act: -0.1700
Data Index: 1789112 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.4704. Min Act: -0.1700
Data Index: 7295542 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.4704. Min Act: -0.1700
Data Index: 7058873 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.4704. Min Act: -0.1700
Data Index: 5115628 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19