Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3079 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0063. Min Range: -1.0063
Max Act: 1.0063. Min Act: -0.1700
Data Index: 6070023 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0063. Min Range: -1.0063
Max Act: 0.9976. Min Act: -0.1700
Data Index: 6070013 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0063. Min Range: -1.0063
Max Act: 1.0063. Min Act: -0.1700
Data Index: 6070014 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0063. Min Range: -1.0063
Max Act: 0.9803. Min Act: -0.1700
Data Index: 6070009 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0063. Min Range: -1.0063
Max Act: 0.9285. Min Act: -0.1700
Data Index: 6070005 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0063. Min Range: -1.0063
Max Act: 0.9028. Min Act: -0.1699
Data Index: 6176042 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0063. Min Range: -1.0063
Max Act: 0.8942. Min Act: -0.1692
Data Index: 2956733 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0063. Min Range: -1.0063
Max Act: 0.8942. Min Act: -0.1692
Data Index: 3549932 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0063. Min Range: -1.0063
Max Act: 0.9028. Min Act: -0.1700
Data Index: 7727158 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0063. Min Range: -1.0063
Max Act: 0.8942. Min Act: -0.1700
Data Index: 6420210 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0063. Min Range: -1.0063
Max Act: 0.8942. Min Act: -0.1700
Data Index: 3499070 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0063. Min Range: -1.0063
Max Act: 0.9028. Min Act: -0.1654
Data Index: 6176054 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0063. Min Range: -1.0063
Max Act: 0.9028. Min Act: -0.1676
Data Index: 7182512 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0063. Min Range: -1.0063
Max Act: 0.8857. Min Act: -0.1696
Data Index: 589975 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0063. Min Range: -1.0063
Max Act: 0.8857. Min Act: -0.1700
Data Index: 4463220 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0063. Min Range: -1.0063
Max Act: 0.8857. Min Act: -0.1700
Data Index: 8001575 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0063. Min Range: -1.0063
Max Act: 0.8857. Min Act: -0.1700
Data Index: 8295949 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0063. Min Range: -1.0063
Max Act: 0.8686. Min Act: -0.1700
Data Index: 6070003 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0063. Min Range: -1.0063
Max Act: 0.8686. Min Act: -0.1694
Data Index: 924944 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0063. Min Range: -1.0063
Max Act: 0.8601. Min Act: -0.1694
Data Index: 1726330 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19