Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3676 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4012. Min Range: -5.4012
Max Act: 5.4012. Min Act: -0.1700
Data Index: 7615686 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4012. Min Range: -5.4012
Max Act: 5.3699. Min Act: -0.1700
Data Index: 8558722 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4012. Min Range: -5.4012
Max Act: 5.3074. Min Act: -0.1700
Data Index: 5939788 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4012. Min Range: -5.4012
Max Act: 5.3074. Min Act: -0.1700
Data Index: 1702879 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4012. Min Range: -5.4012
Max Act: 5.2762. Min Act: -0.1700
Data Index: 4547765 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4012. Min Range: -5.4012
Max Act: 5.2137. Min Act: -0.1700
Data Index: 6990220 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4012. Min Range: -5.4012
Max Act: 5.2137. Min Act: -0.1700
Data Index: 1067436 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4012. Min Range: -5.4012
Max Act: 5.2137. Min Act: -0.1700
Data Index: 4711421 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4012. Min Range: -5.4012
Max Act: 5.1824. Min Act: -0.1700
Data Index: 5003496 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4012. Min Range: -5.4012
Max Act: 5.1824. Min Act: -0.1700
Data Index: 2185277 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4012. Min Range: -5.4012
Max Act: 5.1824. Min Act: -0.1700
Data Index: 4741728 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4012. Min Range: -5.4012
Max Act: 5.1824. Min Act: -0.1700
Data Index: 8824385 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4012. Min Range: -5.4012
Max Act: 5.2137. Min Act: -0.1700
Data Index: 568142 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4012. Min Range: -5.4012
Max Act: 5.2137. Min Act: -0.1700
Data Index: 373101 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4012. Min Range: -5.4012
Max Act: 5.1512. Min Act: -0.1700
Data Index: 4363624 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4012. Min Range: -5.4012
Max Act: 5.1512. Min Act: -0.1700
Data Index: 2764544 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4012. Min Range: -5.4012
Max Act: 5.1512. Min Act: -0.1700
Data Index: 7397388 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4012. Min Range: -5.4012
Max Act: 5.1199. Min Act: -0.1700
Data Index: 6410185 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4012. Min Range: -5.4012
Max Act: 5.1199. Min Act: -0.1700
Data Index: 6204663 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4012. Min Range: -5.4012
Max Act: 5.1199. Min Act: -0.1700
Data Index: 6446949 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19