Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1988 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3778. Min Range: -6.3778
Max Act: 6.3778. Min Act: -0.1700
Data Index: 472859 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3778. Min Range: -6.3778
Max Act: 6.2840. Min Act: -0.1700
Data Index: 472889 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3778. Min Range: -6.3778
Max Act: 6.2215. Min Act: -0.1700
Data Index: 5661013 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3778. Min Range: -6.3778
Max Act: 6.1903. Min Act: -0.1700
Data Index: 472862 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3778. Min Range: -6.3778
Max Act: 6.1590. Min Act: -0.1699
Data Index: 472865 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3778. Min Range: -6.3778
Max Act: 6.1903. Min Act: -0.1699
Data Index: 2050270 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3778. Min Range: -6.3778
Max Act: 6.1590. Min Act: -0.1700
Data Index: 472868 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3778. Min Range: -6.3778
Max Act: 6.1590. Min Act: -0.1700
Data Index: 5509498 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3778. Min Range: -6.3778
Max Act: 6.1278. Min Act: -0.1700
Data Index: 6798422 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3778. Min Range: -6.3778
Max Act: 6.0965. Min Act: -0.1700
Data Index: 7837963 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3778. Min Range: -6.3778
Max Act: 6.0965. Min Act: -0.1700
Data Index: 472879 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3778. Min Range: -6.3778
Max Act: 6.0653. Min Act: -0.1700
Data Index: 1700308 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3778. Min Range: -6.3778
Max Act: 6.0653. Min Act: -0.1700
Data Index: 6161938 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3778. Min Range: -6.3778
Max Act: 6.0028. Min Act: -0.1700
Data Index: 5991166 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3778. Min Range: -6.3778
Max Act: 6.0340. Min Act: -0.1700
Data Index: 472882 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3778. Min Range: -6.3778
Max Act: 6.0028. Min Act: -0.1700
Data Index: 2075287 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3778. Min Range: -6.3778
Max Act: 6.0028. Min Act: -0.1700
Data Index: 8029469 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3778. Min Range: -6.3778
Max Act: 6.0028. Min Act: -0.1700
Data Index: 763711 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3778. Min Range: -6.3778
Max Act: 5.9715. Min Act: -0.1700
Data Index: 472885 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3778. Min Range: -6.3778
Max Act: 5.9403. Min Act: -0.1700
Data Index: 1122053 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19