Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1497 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.3645. Min Act: -0.1700
Data Index: 8770418 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.2707. Min Act: -0.1700
Data Index: 7829691 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.2082. Min Act: -0.1700
Data Index: 5804137 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.1145. Min Act: -0.1700
Data Index: 5953458 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0832. Min Act: -0.1700
Data Index: 1918930 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0832. Min Act: -0.1700
Data Index: 3101346 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0832. Min Act: -0.1700
Data Index: 3186307 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0832. Min Act: -0.1700
Data Index: 6782083 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0520. Min Act: -0.1700
Data Index: 6707457 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0520. Min Act: -0.1700
Data Index: 331386 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0520. Min Act: -0.1700
Data Index: 3522365 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0520. Min Act: -0.1700
Data Index: 8676855 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0520. Min Act: -0.1700
Data Index: 4137043 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0520. Min Act: -0.1700
Data Index: 7196516 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0520. Min Act: -0.1700
Data Index: 6566960 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0520. Min Act: -0.1700
Data Index: 890004 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0520. Min Act: -0.1700
Data Index: 5996426 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0520. Min Act: -0.1700
Data Index: 5624665 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0520. Min Act: -0.1700
Data Index: 4709601 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0520. Min Act: -0.1700
Data Index: 5937988 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19