Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2318 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.1615. Min Range: -14.1615
Max Act: 14.1615. Min Act: -0.1700
Data Index: 7104118 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.1615. Min Range: -14.1615
Max Act: 14.1615. Min Act: -0.1700
Data Index: 1205980 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.1615. Min Range: -14.1615
Max Act: 13.5990. Min Act: -0.1700
Data Index: 5980909 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.1615. Min Range: -14.1615
Max Act: 13.6615. Min Act: -0.1700
Data Index: 6473680 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.1615. Min Range: -14.1615
Max Act: 13.4115. Min Act: -0.1700
Data Index: 6083248 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.1615. Min Range: -14.1615
Max Act: 13.2865. Min Act: -0.1700
Data Index: 2762895 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.1615. Min Range: -14.1615
Max Act: 13.2865. Min Act: -0.1700
Data Index: 6140899 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.1615. Min Range: -14.1615
Max Act: 13.2240. Min Act: -0.1700
Data Index: 6004654 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.1615. Min Range: -14.1615
Max Act: 13.2240. Min Act: -0.1700
Data Index: 3650512 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.1615. Min Range: -14.1615
Max Act: 13.2240. Min Act: -0.1700
Data Index: 8372722 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.1615. Min Range: -14.1615
Max Act: 13.0365. Min Act: -0.1700
Data Index: 8142658 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.1615. Min Range: -14.1615
Max Act: 13.0365. Min Act: -0.1700
Data Index: 4734164 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.1615. Min Range: -14.1615
Max Act: 13.0365. Min Act: -0.1700
Data Index: 5048077 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.1615. Min Range: -14.1615
Max Act: 13.0365. Min Act: -0.1700
Data Index: 8738057 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.1615. Min Range: -14.1615
Max Act: 13.0365. Min Act: -0.1700
Data Index: 2435422 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.1615. Min Range: -14.1615
Max Act: 12.9740. Min Act: -0.1700
Data Index: 460843 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.1615. Min Range: -14.1615
Max Act: 12.9740. Min Act: -0.1700
Data Index: 5381642 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.1615. Min Range: -14.1615
Max Act: 12.9115. Min Act: -0.1700
Data Index: 2128264 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.1615. Min Range: -14.1615
Max Act: 12.9115. Min Act: -0.1700
Data Index: 7015693 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.1615. Min Range: -14.1615
Max Act: 12.9740. Min Act: -0.1700
Data Index: 567041 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19