Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3630 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2841. Min Range: -4.2841
Max Act: 4.2841. Min Act: -0.1700
Data Index: 6525982 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2841. Min Range: -4.2841
Max Act: 4.2841. Min Act: -0.1700
Data Index: 6917776 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2841. Min Range: -4.2841
Max Act: 4.2841. Min Act: -0.1700
Data Index: 7483022 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2841. Min Range: -4.2841
Max Act: 4.1278. Min Act: -0.1700
Data Index: 1654357 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2841. Min Range: -4.2841
Max Act: 4.1590. Min Act: -0.1700
Data Index: 2675389 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2841. Min Range: -4.2841
Max Act: 4.1590. Min Act: -0.1700
Data Index: 6880204 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2841. Min Range: -4.2841
Max Act: 4.0965. Min Act: -0.1700
Data Index: 6619995 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2841. Min Range: -4.2841
Max Act: 4.0653. Min Act: -0.1700
Data Index: 3054741 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2841. Min Range: -4.2841
Max Act: 4.0340. Min Act: -0.1700
Data Index: 71779 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2841. Min Range: -4.2841
Max Act: 4.0653. Min Act: -0.1700
Data Index: 4786666 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2841. Min Range: -4.2841
Max Act: 4.0340. Min Act: -0.1700
Data Index: 1548845 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2841. Min Range: -4.2841
Max Act: 4.0340. Min Act: -0.1700
Data Index: 6769493 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2841. Min Range: -4.2841
Max Act: 4.0028. Min Act: -0.1700
Data Index: 7788640 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2841. Min Range: -4.2841
Max Act: 4.0028. Min Act: -0.1700
Data Index: 2675117 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2841. Min Range: -4.2841
Max Act: 4.0028. Min Act: -0.1700
Data Index: 8107010 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2841. Min Range: -4.2841
Max Act: 4.0028. Min Act: -0.1700
Data Index: 7389382 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2841. Min Range: -4.2841
Max Act: 4.0340. Min Act: -0.1700
Data Index: 7068749 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2841. Min Range: -4.2841
Max Act: 3.9715. Min Act: -0.1700
Data Index: 7807453 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2841. Min Range: -4.2841
Max Act: 3.9402. Min Act: -0.1700
Data Index: 6073142 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2841. Min Range: -4.2841
Max Act: 3.9715. Min Act: -0.1700
Data Index: 5501892 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19