Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3483 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7697. Min Range: -5.7697
Max Act: 5.7697. Min Act: -0.1700
Data Index: 7969596 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7697. Min Range: -5.7697
Max Act: 5.7697. Min Act: -0.1700
Data Index: 176070 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7697. Min Range: -5.7697
Max Act: 5.7697. Min Act: -0.1700
Data Index: 1693331 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7697. Min Range: -5.7697
Max Act: 5.7697. Min Act: -0.1699
Data Index: 1965132 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7697. Min Range: -5.7697
Max Act: 5.7385. Min Act: -0.1700
Data Index: 7857658 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7697. Min Range: -5.7697
Max Act: 5.7072. Min Act: -0.1695
Data Index: 7029739 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7697. Min Range: -5.7697
Max Act: 5.7385. Min Act: -0.1699
Data Index: 3752591 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7697. Min Range: -5.7697
Max Act: 5.6447. Min Act: -0.1700
Data Index: 6807237 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7697. Min Range: -5.7697
Max Act: 5.7072. Min Act: -0.1698
Data Index: 312999 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7697. Min Range: -5.7697
Max Act: 5.6447. Min Act: -0.1700
Data Index: 3871741 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7697. Min Range: -5.7697
Max Act: 5.6447. Min Act: -0.1699
Data Index: 4632971 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7697. Min Range: -5.7697
Max Act: 5.6135. Min Act: -0.1700
Data Index: 5370646 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7697. Min Range: -5.7697
Max Act: 5.6135. Min Act: -0.1699
Data Index: 4139239 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7697. Min Range: -5.7697
Max Act: 5.6135. Min Act: -0.1695
Data Index: 530239 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7697. Min Range: -5.7697
Max Act: 5.6135. Min Act: -0.1699
Data Index: 6984203 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7697. Min Range: -5.7697
Max Act: 5.6135. Min Act: -0.1700
Data Index: 4118552 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7697. Min Range: -5.7697
Max Act: 5.5822. Min Act: -0.1696
Data Index: 6297889 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7697. Min Range: -5.7697
Max Act: 5.5822. Min Act: -0.1700
Data Index: 4590128 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7697. Min Range: -5.7697
Max Act: 5.5822. Min Act: -0.1700
Data Index: 4547951 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7697. Min Range: -5.7697
Max Act: 5.5510. Min Act: -0.1700
Data Index: 262748 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19