Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5596 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1468. Min Range: -4.1468
Max Act: 4.1468. Min Act: -0.1700
Data Index: 7123743 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1468. Min Range: -4.1468
Max Act: 4.1468. Min Act: -0.1700
Data Index: 4184309 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1468. Min Range: -4.1468
Max Act: 4.1468. Min Act: -0.1688
Data Index: 4161273 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1468. Min Range: -4.1468
Max Act: 4.1468. Min Act: -0.1691
Data Index: 4050021 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1468. Min Range: -4.1468
Max Act: 4.1468. Min Act: -0.1699
Data Index: 3751731 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1468. Min Range: -4.1468
Max Act: 4.1468. Min Act: -0.1700
Data Index: 3666436 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1468. Min Range: -4.1468
Max Act: 4.1468. Min Act: -0.1700
Data Index: 5590648 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1468. Min Range: -4.1468
Max Act: 4.1468. Min Act: -0.1700
Data Index: 3459617 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1468. Min Range: -4.1468
Max Act: 4.1468. Min Act: -0.1700
Data Index: 3309778 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1468. Min Range: -4.1468
Max Act: 4.1468. Min Act: -0.1700
Data Index: 7123758 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1468. Min Range: -4.1468
Max Act: 4.1468. Min Act: -0.1700
Data Index: 1427664 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1468. Min Range: -4.1468
Max Act: 4.1468. Min Act: -0.1700
Data Index: 6966995 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1468. Min Range: -4.1468
Max Act: 4.1468. Min Act: -0.1700
Data Index: 2766689 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1468. Min Range: -4.1468
Max Act: 4.1468. Min Act: -0.1699
Data Index: 2758157 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1468. Min Range: -4.1468
Max Act: 4.1468. Min Act: -0.1700
Data Index: 2211005 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1468. Min Range: -4.1468
Max Act: 4.1468. Min Act: -0.1700
Data Index: 2193747 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1468. Min Range: -4.1468
Max Act: 4.1468. Min Act: -0.1700
Data Index: 2098979 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1468. Min Range: -4.1468
Max Act: 4.1468. Min Act: -0.1700
Data Index: 4365961 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1468. Min Range: -4.1468
Max Act: 4.1468. Min Act: -0.1671
Data Index: 5766633 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1468. Min Range: -4.1468
Max Act: 4.1468. Min Act: -0.1700
Data Index: 1427667 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19