Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 779 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.8006. Min Range: -7.8006
Max Act: 7.8006. Min Act: -0.1699
Data Index: 345521 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8006. Min Range: -7.8006
Max Act: 7.6756. Min Act: -0.1700
Data Index: 5402822 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8006. Min Range: -7.8006
Max Act: 7.4881. Min Act: -0.1700
Data Index: 6080756 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8006. Min Range: -7.8006
Max Act: 7.4881. Min Act: -0.1700
Data Index: 7302754 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8006. Min Range: -7.8006
Max Act: 7.4881. Min Act: -0.1674
Data Index: 5073029 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8006. Min Range: -7.8006
Max Act: 7.4881. Min Act: -0.1700
Data Index: 4441376 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8006. Min Range: -7.8006
Max Act: 7.4256. Min Act: -0.1700
Data Index: 7302762 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8006. Min Range: -7.8006
Max Act: 7.3631. Min Act: -0.1700
Data Index: 1115909 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8006. Min Range: -7.8006
Max Act: 7.3631. Min Act: -0.1700
Data Index: 4994056 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8006. Min Range: -7.8006
Max Act: 7.3631. Min Act: -0.1670
Data Index: 8717825 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8006. Min Range: -7.8006
Max Act: 7.3631. Min Act: -0.1699
Data Index: 7432073 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8006. Min Range: -7.8006
Max Act: 7.3631. Min Act: -0.1700
Data Index: 2010983 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8006. Min Range: -7.8006
Max Act: 7.4256. Min Act: -0.1700
Data Index: 1966102 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8006. Min Range: -7.8006
Max Act: 7.3631. Min Act: -0.1700
Data Index: 1702777 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8006. Min Range: -7.8006
Max Act: 7.3631. Min Act: -0.1700
Data Index: 3728306 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8006. Min Range: -7.8006
Max Act: 7.3631. Min Act: -0.1700
Data Index: 5521074 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8006. Min Range: -7.8006
Max Act: 7.3631. Min Act: -0.1698
Data Index: 1576057 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8006. Min Range: -7.8006
Max Act: 7.3631. Min Act: -0.1693
Data Index: 2495980 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8006. Min Range: -7.8006
Max Act: 7.3631. Min Act: -0.1683
Data Index: 1218736 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8006. Min Range: -7.8006
Max Act: 7.4256. Min Act: -0.1698
Data Index: 2269411 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19