Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1377 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9839. Min Range: -5.9839
Max Act: 5.9839. Min Act: -0.1700
Data Index: 5232795 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9839. Min Range: -5.9839
Max Act: 5.8276. Min Act: -0.1680
Data Index: 6026916 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9839. Min Range: -5.9839
Max Act: 5.7964. Min Act: -0.1700
Data Index: 7142313 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9839. Min Range: -5.9839
Max Act: 5.7964. Min Act: -0.1700
Data Index: 2021448 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9839. Min Range: -5.9839
Max Act: 5.7651. Min Act: -0.1700
Data Index: 5033156 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9839. Min Range: -5.9839
Max Act: 5.7339. Min Act: -0.1700
Data Index: 6813634 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9839. Min Range: -5.9839
Max Act: 5.7339. Min Act: -0.1691
Data Index: 5844759 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9839. Min Range: -5.9839
Max Act: 5.6714. Min Act: -0.1700
Data Index: 7382820 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9839. Min Range: -5.9839
Max Act: 5.6714. Min Act: -0.1700
Data Index: 2542826 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9839. Min Range: -5.9839
Max Act: 5.6714. Min Act: -0.1700
Data Index: 1986186 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9839. Min Range: -5.9839
Max Act: 5.6714. Min Act: -0.1700
Data Index: 7098526 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9839. Min Range: -5.9839
Max Act: 5.6401. Min Act: -0.1700
Data Index: 5893889 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9839. Min Range: -5.9839
Max Act: 5.6714. Min Act: -0.1700
Data Index: 5544056 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9839. Min Range: -5.9839
Max Act: 5.6401. Min Act: -0.1700
Data Index: 8259437 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9839. Min Range: -5.9839
Max Act: 5.6089. Min Act: -0.1700
Data Index: 4900746 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9839. Min Range: -5.9839
Max Act: 5.6089. Min Act: -0.1506
Data Index: 3696561 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9839. Min Range: -5.9839
Max Act: 5.6401. Min Act: -0.1700
Data Index: 8702076 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9839. Min Range: -5.9839
Max Act: 5.5776. Min Act: -0.1699
Data Index: 1596818 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9839. Min Range: -5.9839
Max Act: 5.5776. Min Act: -0.1700
Data Index: 6152493 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9839. Min Range: -5.9839
Max Act: 5.5776. Min Act: -0.1700
Data Index: 198137 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19