Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3502 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4794. Min Range: -5.4794
Max Act: 5.4794. Min Act: -0.1700
Data Index: 3094831 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4794. Min Range: -5.4794
Max Act: 5.3232. Min Act: -0.1700
Data Index: 2289718 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4794. Min Range: -5.4794
Max Act: 5.2919. Min Act: -0.1700
Data Index: 3165502 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4794. Min Range: -5.4794
Max Act: 5.2294. Min Act: -0.1700
Data Index: 2959180 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4794. Min Range: -5.4794
Max Act: 5.1982. Min Act: -0.1700
Data Index: 2710565 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4794. Min Range: -5.4794
Max Act: 5.1982. Min Act: -0.1700
Data Index: 3754714 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4794. Min Range: -5.4794
Max Act: 5.1982. Min Act: -0.1700
Data Index: 5704810 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4794. Min Range: -5.4794
Max Act: 5.1669. Min Act: -0.1700
Data Index: 3604972 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4794. Min Range: -5.4794
Max Act: 5.1669. Min Act: -0.1700
Data Index: 3604981 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4794. Min Range: -5.4794
Max Act: 5.1357. Min Act: -0.1700
Data Index: 8070624 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4794. Min Range: -5.4794
Max Act: 5.1357. Min Act: -0.1699
Data Index: 3165507 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4794. Min Range: -5.4794
Max Act: 5.1357. Min Act: -0.1700
Data Index: 1416406 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4794. Min Range: -5.4794
Max Act: 5.1357. Min Act: -0.1697
Data Index: 3165491 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4794. Min Range: -5.4794
Max Act: 5.1044. Min Act: -0.1700
Data Index: 3604966 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4794. Min Range: -5.4794
Max Act: 5.1044. Min Act: -0.1700
Data Index: 3604956 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4794. Min Range: -5.4794
Max Act: 5.1044. Min Act: -0.1700
Data Index: 3794326 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4794. Min Range: -5.4794
Max Act: 5.1044. Min Act: -0.1700
Data Index: 3165504 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4794. Min Range: -5.4794
Max Act: 5.1044. Min Act: -0.1700
Data Index: 6249103 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4794. Min Range: -5.4794
Max Act: 5.1044. Min Act: -0.1700
Data Index: 3165519 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4794. Min Range: -5.4794
Max Act: 5.1044. Min Act: -0.1700
Data Index: 3378128 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19