Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3787 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3062. Min Range: -5.3062
Max Act: 5.3062. Min Act: -0.1700
Data Index: 3687431 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3062. Min Range: -5.3062
Max Act: 5.3062. Min Act: -0.1700
Data Index: 4947655 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3062. Min Range: -5.3062
Max Act: 5.3062. Min Act: -0.1700
Data Index: 7648572 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3062. Min Range: -5.3062
Max Act: 5.2124. Min Act: -0.1698
Data Index: 6074181 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3062. Min Range: -5.3062
Max Act: 5.2124. Min Act: -0.1698
Data Index: 4248503 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3062. Min Range: -5.3062
Max Act: 5.2124. Min Act: -0.1700
Data Index: 4710936 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3062. Min Range: -5.3062
Max Act: 5.2124. Min Act: -0.1700
Data Index: 1550200 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3062. Min Range: -5.3062
Max Act: 5.2124. Min Act: -0.1700
Data Index: 1141184 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3062. Min Range: -5.3062
Max Act: 5.1812. Min Act: -0.1700
Data Index: 2765942 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3062. Min Range: -5.3062
Max Act: 5.1812. Min Act: -0.1700
Data Index: 6452500 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3062. Min Range: -5.3062
Max Act: 5.1499. Min Act: -0.1695
Data Index: 4947549 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3062. Min Range: -5.3062
Max Act: 5.1812. Min Act: -0.1700
Data Index: 5993053 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3062. Min Range: -5.3062
Max Act: 5.1812. Min Act: -0.1700
Data Index: 3369490 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3062. Min Range: -5.3062
Max Act: 5.1499. Min Act: -0.1700
Data Index: 5856947 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3062. Min Range: -5.3062
Max Act: 5.1499. Min Act: -0.1700
Data Index: 8297898 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3062. Min Range: -5.3062
Max Act: 5.1499. Min Act: -0.1700
Data Index: 7777403 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3062. Min Range: -5.3062
Max Act: 5.1499. Min Act: -0.1688
Data Index: 5240870 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3062. Min Range: -5.3062
Max Act: 5.1499. Min Act: -0.1700
Data Index: 5132738 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3062. Min Range: -5.3062
Max Act: 5.1499. Min Act: -0.1700
Data Index: 3984101 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3062. Min Range: -5.3062
Max Act: 5.1499. Min Act: -0.1700
Data Index: 117403 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19