Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2007 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.8298. Min Act: -0.1700
Data Index: 4297743 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.8298. Min Act: -0.1700
Data Index: 6369741 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.7985. Min Act: -0.1700
Data Index: 7800053 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.7672. Min Act: -0.1700
Data Index: 1153857 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.7672. Min Act: -0.1700
Data Index: 1380633 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.7672. Min Act: -0.1700
Data Index: 6233676 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.7359. Min Act: -0.1700
Data Index: 4647980 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.7359. Min Act: -0.1700
Data Index: 1577210 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.7047. Min Act: -0.1700
Data Index: 5195905 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.7047. Min Act: -0.1700
Data Index: 1153860 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.7047. Min Act: -0.1700
Data Index: 4615432 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.6734. Min Act: -0.1700
Data Index: 3432607 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.6734. Min Act: -0.1700
Data Index: 5918440 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.6734. Min Act: -0.1700
Data Index: 2921265 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.6734. Min Act: -0.1700
Data Index: 6954647 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.6734. Min Act: -0.1700
Data Index: 642763 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.6734. Min Act: -0.1700
Data Index: 4811090 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.6734. Min Act: -0.1700
Data Index: 4541220 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.6734. Min Act: -0.1700
Data Index: 1856918 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.6421. Min Act: -0.1700
Data Index: 4529061 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19