Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5312 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2007. Min Range: -5.2007
Max Act: 5.2007. Min Act: -0.1700
Data Index: 3631645 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2007. Min Range: -5.2007
Max Act: 5.1382. Min Act: -0.1700
Data Index: 5422194 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2007. Min Range: -5.2007
Max Act: 5.1069. Min Act: -0.1700
Data Index: 1708811 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2007. Min Range: -5.2007
Max Act: 5.1069. Min Act: -0.1700
Data Index: 4275172 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2007. Min Range: -5.2007
Max Act: 5.0757. Min Act: -0.1700
Data Index: 4286543 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2007. Min Range: -5.2007
Max Act: 5.0757. Min Act: -0.1700
Data Index: 5041246 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2007. Min Range: -5.2007
Max Act: 5.0132. Min Act: -0.1700
Data Index: 878968 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2007. Min Range: -5.2007
Max Act: 4.9819. Min Act: -0.1700
Data Index: 6532086 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2007. Min Range: -5.2007
Max Act: 4.9819. Min Act: -0.1700
Data Index: 108022 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2007. Min Range: -5.2007
Max Act: 4.9507. Min Act: -0.1700
Data Index: 7849283 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2007. Min Range: -5.2007
Max Act: 4.9507. Min Act: -0.1700
Data Index: 1141850 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2007. Min Range: -5.2007
Max Act: 4.9194. Min Act: -0.1700
Data Index: 1933023 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2007. Min Range: -5.2007
Max Act: 4.9194. Min Act: -0.1700
Data Index: 1493372 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2007. Min Range: -5.2007
Max Act: 4.9194. Min Act: -0.1700
Data Index: 211864 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2007. Min Range: -5.2007
Max Act: 4.9194. Min Act: -0.1700
Data Index: 7695483 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2007. Min Range: -5.2007
Max Act: 4.8882. Min Act: -0.1700
Data Index: 354050 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2007. Min Range: -5.2007
Max Act: 4.8882. Min Act: -0.1700
Data Index: 7822572 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2007. Min Range: -5.2007
Max Act: 4.8882. Min Act: -0.1700
Data Index: 4245062 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2007. Min Range: -5.2007
Max Act: 4.8882. Min Act: -0.1700
Data Index: 1099028 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2007. Min Range: -5.2007
Max Act: 4.8882. Min Act: -0.1700
Data Index: 1327211 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19