Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1680 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7876. Min Range: -2.7876
Max Act: 2.7876. Min Act: -0.1700
Data Index: 3457193 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7876. Min Range: -2.7876
Max Act: 2.7398. Min Act: -0.1700
Data Index: 6890740 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7876. Min Range: -2.7876
Max Act: 2.7398. Min Act: -0.1700
Data Index: 4025181 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7876. Min Range: -2.7876
Max Act: 2.7238. Min Act: -0.1700
Data Index: 2546626 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7876. Min Range: -2.7876
Max Act: 2.7078. Min Act: -0.1700
Data Index: 3823856 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7876. Min Range: -2.7876
Max Act: 2.7238. Min Act: -0.1700
Data Index: 4105010 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7876. Min Range: -2.7876
Max Act: 2.7238. Min Act: -0.1700
Data Index: 6608896 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7876. Min Range: -2.7876
Max Act: 2.7238. Min Act: -0.1700
Data Index: 6560304 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7876. Min Range: -2.7876
Max Act: 2.7078. Min Act: -0.1700
Data Index: 743415 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7876. Min Range: -2.7876
Max Act: 2.7078. Min Act: -0.1700
Data Index: 8074180 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7876. Min Range: -2.7876
Max Act: 2.6918. Min Act: -0.1700
Data Index: 5892317 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7876. Min Range: -2.7876
Max Act: 2.6918. Min Act: -0.1700
Data Index: 3260050 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7876. Min Range: -2.7876
Max Act: 2.6758. Min Act: -0.1700
Data Index: 280766 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7876. Min Range: -2.7876
Max Act: 2.6918. Min Act: -0.1700
Data Index: 2080849 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7876. Min Range: -2.7876
Max Act: 2.6918. Min Act: -0.1700
Data Index: 1645987 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7876. Min Range: -2.7876
Max Act: 2.6918. Min Act: -0.1700
Data Index: 1708592 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7876. Min Range: -2.7876
Max Act: 2.6918. Min Act: -0.1700
Data Index: 7203236 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7876. Min Range: -2.7876
Max Act: 2.6758. Min Act: -0.1700
Data Index: 5540618 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7876. Min Range: -2.7876
Max Act: 2.6758. Min Act: -0.1700
Data Index: 6239944 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7876. Min Range: -2.7876
Max Act: 2.6758. Min Act: -0.1700
Data Index: 4611887 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19