Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3802 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9830. Min Range: -7.9830
Max Act: 7.9830. Min Act: -0.1700
Data Index: 5385992 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9830. Min Range: -7.9830
Max Act: 7.6705. Min Act: -0.1700
Data Index: 5041814 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9830. Min Range: -7.9830
Max Act: 7.7330. Min Act: -0.1700
Data Index: 1639927 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9830. Min Range: -7.9830
Max Act: 7.5455. Min Act: -0.1700
Data Index: 6200909 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9830. Min Range: -7.9830
Max Act: 7.4830. Min Act: -0.1700
Data Index: 3903896 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9830. Min Range: -7.9830
Max Act: 7.4517. Min Act: -0.1700
Data Index: 3179530 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9830. Min Range: -7.9830
Max Act: 7.4517. Min Act: -0.1700
Data Index: 2155801 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9830. Min Range: -7.9830
Max Act: 7.4205. Min Act: -0.1700
Data Index: 1148201 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9830. Min Range: -7.9830
Max Act: 7.3892. Min Act: -0.1700
Data Index: 3564973 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9830. Min Range: -7.9830
Max Act: 7.3892. Min Act: -0.1700
Data Index: 4299345 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9830. Min Range: -7.9830
Max Act: 7.3580. Min Act: -0.1700
Data Index: 8008167 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9830. Min Range: -7.9830
Max Act: 7.3580. Min Act: -0.1700
Data Index: 866118 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9830. Min Range: -7.9830
Max Act: 7.3580. Min Act: -0.1700
Data Index: 1285156 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9830. Min Range: -7.9830
Max Act: 7.3580. Min Act: -0.1700
Data Index: 676083 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9830. Min Range: -7.9830
Max Act: 7.3580. Min Act: -0.1700
Data Index: 8224564 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9830. Min Range: -7.9830
Max Act: 7.3267. Min Act: -0.1700
Data Index: 3886075 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9830. Min Range: -7.9830
Max Act: 7.2642. Min Act: -0.1700
Data Index: 3902602 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9830. Min Range: -7.9830
Max Act: 7.2642. Min Act: -0.1700
Data Index: 326414 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9830. Min Range: -7.9830
Max Act: 7.2330. Min Act: -0.1700
Data Index: 3616590 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9830. Min Range: -7.9830
Max Act: 7.2955. Min Act: -0.1700
Data Index: 3616597 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19