Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5664 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9824. Min Range: -6.9824
Max Act: 6.9824. Min Act: -0.1700
Data Index: 1567184 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9824. Min Range: -6.9824
Max Act: 6.9824. Min Act: -0.1700
Data Index: 4980674 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9824. Min Range: -6.9824
Max Act: 6.9824. Min Act: -0.1700
Data Index: 2624387 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9824. Min Range: -6.9824
Max Act: 6.9511. Min Act: -0.1700
Data Index: 6390783 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9824. Min Range: -6.9824
Max Act: 6.9511. Min Act: -0.1700
Data Index: 5425107 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9824. Min Range: -6.9824
Max Act: 6.9511. Min Act: -0.1700
Data Index: 1498628 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9824. Min Range: -6.9824
Max Act: 6.9824. Min Act: -0.1700
Data Index: 7055885 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9824. Min Range: -6.9824
Max Act: 6.8886. Min Act: -0.1700
Data Index: 7156491 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9824. Min Range: -6.9824
Max Act: 6.8574. Min Act: -0.1700
Data Index: 1974865 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9824. Min Range: -6.9824
Max Act: 6.7949. Min Act: -0.1700
Data Index: 7765902 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9824. Min Range: -6.9824
Max Act: 6.7949. Min Act: -0.1700
Data Index: 2564906 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9824. Min Range: -6.9824
Max Act: 6.7949. Min Act: -0.1700
Data Index: 2443720 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9824. Min Range: -6.9824
Max Act: 6.7324. Min Act: -0.1700
Data Index: 1592081 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9824. Min Range: -6.9824
Max Act: 6.7636. Min Act: -0.1700
Data Index: 5501849 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9824. Min Range: -6.9824
Max Act: 6.7324. Min Act: -0.1700
Data Index: 8280608 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9824. Min Range: -6.9824
Max Act: 6.7324. Min Act: -0.1700
Data Index: 2198555 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9824. Min Range: -6.9824
Max Act: 6.7324. Min Act: -0.1700
Data Index: 1330307 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9824. Min Range: -6.9824
Max Act: 6.7636. Min Act: -0.1700
Data Index: 6187826 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9824. Min Range: -6.9824
Max Act: 6.6699. Min Act: -0.1700
Data Index: 7859150 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9824. Min Range: -6.9824
Max Act: 6.6699. Min Act: -0.1700
Data Index: 3749661 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19