Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1805 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.8610. Min Act: -0.1699
Data Index: 7867210 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7985. Min Act: -0.1700
Data Index: 4635985 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7985. Min Act: -0.1700
Data Index: 4416662 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7985. Min Act: -0.1698
Data Index: 1486416 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7985. Min Act: -0.1700
Data Index: 769631 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7985. Min Act: -0.1700
Data Index: 3630096 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7985. Min Act: -0.1700
Data Index: 5499879 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7985. Min Act: -0.1700
Data Index: 1978400 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7985. Min Act: -0.1700
Data Index: 8623357 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7985. Min Act: -0.1700
Data Index: 5405636 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7985. Min Act: -0.1700
Data Index: 8037829 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7985. Min Act: -0.1700
Data Index: 6961502 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7360. Min Act: -0.1700
Data Index: 2947240 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7360. Min Act: -0.1700
Data Index: 3087249 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7360. Min Act: -0.1700
Data Index: 3518245 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7360. Min Act: -0.1700
Data Index: 3566666 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7360. Min Act: -0.1700
Data Index: 5561960 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7360. Min Act: -0.1700
Data Index: 3758224 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7360. Min Act: -0.1700
Data Index: 4173526 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7360. Min Act: -0.1697
Data Index: 6958083 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19