Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6098 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0315. Min Range: -4.0315
Max Act: 4.0315. Min Act: -0.1700
Data Index: 1275865 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0315. Min Range: -4.0315
Max Act: 4.0315. Min Act: -0.1700
Data Index: 7248554 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0315. Min Range: -4.0315
Max Act: 4.0003. Min Act: -0.1700
Data Index: 7006591 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0315. Min Range: -4.0315
Max Act: 4.0315. Min Act: -0.1700
Data Index: 6393820 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0315. Min Range: -4.0315
Max Act: 4.0315. Min Act: -0.1700
Data Index: 1385708 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0315. Min Range: -4.0315
Max Act: 4.0315. Min Act: -0.1700
Data Index: 5254014 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0315. Min Range: -4.0315
Max Act: 4.0315. Min Act: -0.1700
Data Index: 3565214 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0315. Min Range: -4.0315
Max Act: 4.0315. Min Act: -0.1700
Data Index: 7680408 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0315. Min Range: -4.0315
Max Act: 4.0315. Min Act: -0.1700
Data Index: 1699492 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0315. Min Range: -4.0315
Max Act: 4.0315. Min Act: -0.1700
Data Index: 4583126 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0315. Min Range: -4.0315
Max Act: 3.9378. Min Act: -0.1700
Data Index: 7589834 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0315. Min Range: -4.0315
Max Act: 3.9065. Min Act: -0.1700
Data Index: 7288110 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0315. Min Range: -4.0315
Max Act: 3.8752. Min Act: -0.1700
Data Index: 2092237 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0315. Min Range: -4.0315
Max Act: 3.8752. Min Act: -0.1700
Data Index: 4420761 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0315. Min Range: -4.0315
Max Act: 3.8440. Min Act: -0.1700
Data Index: 3145432 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0315. Min Range: -4.0315
Max Act: 3.8127. Min Act: -0.1700
Data Index: 3666931 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0315. Min Range: -4.0315
Max Act: 3.8440. Min Act: -0.1700
Data Index: 711680 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0315. Min Range: -4.0315
Max Act: 3.8127. Min Act: -0.1700
Data Index: 1736722 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0315. Min Range: -4.0315
Max Act: 3.8127. Min Act: -0.1700
Data Index: 2751515 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0315. Min Range: -4.0315
Max Act: 3.8127. Min Act: -0.1700
Data Index: 8676934 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19