Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3640 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7795. Min Range: -7.7795
Max Act: 7.7795. Min Act: -0.1700
Data Index: 267015 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7795. Min Range: -7.7795
Max Act: 7.7170. Min Act: -0.1700
Data Index: 1436821 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7795. Min Range: -7.7795
Max Act: 7.6858. Min Act: -0.1700
Data Index: 1345829 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7795. Min Range: -7.7795
Max Act: 7.5920. Min Act: -0.1700
Data Index: 5583077 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7795. Min Range: -7.7795
Max Act: 7.6233. Min Act: -0.1700
Data Index: 1345828 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7795. Min Range: -7.7795
Max Act: 7.5920. Min Act: -0.1700
Data Index: 2171775 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7795. Min Range: -7.7795
Max Act: 7.4983. Min Act: -0.1700
Data Index: 5047986 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7795. Min Range: -7.7795
Max Act: 7.4045. Min Act: -0.1700
Data Index: 1345839 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7795. Min Range: -7.7795
Max Act: 7.4045. Min Act: -0.1700
Data Index: 5034139 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7795. Min Range: -7.7795
Max Act: 7.3733. Min Act: -0.1700
Data Index: 3547761 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7795. Min Range: -7.7795
Max Act: 7.3733. Min Act: -0.1700
Data Index: 4845290 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7795. Min Range: -7.7795
Max Act: 7.3108. Min Act: -0.1700
Data Index: 2463434 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7795. Min Range: -7.7795
Max Act: 7.3108. Min Act: -0.1700
Data Index: 952344 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7795. Min Range: -7.7795
Max Act: 7.3108. Min Act: -0.1700
Data Index: 7911519 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7795. Min Range: -7.7795
Max Act: 7.2795. Min Act: -0.1700
Data Index: 2636964 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7795. Min Range: -7.7795
Max Act: 7.2483. Min Act: -0.1700
Data Index: 8640709 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7795. Min Range: -7.7795
Max Act: 7.2483. Min Act: -0.1700
Data Index: 3115688 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7795. Min Range: -7.7795
Max Act: 7.2483. Min Act: -0.1700
Data Index: 1633911 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7795. Min Range: -7.7795
Max Act: 7.2170. Min Act: -0.1700
Data Index: 1924867 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7795. Min Range: -7.7795
Max Act: 7.1858. Min Act: -0.1700
Data Index: 5698705 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19