Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3224 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4731. Min Range: -10.4731
Max Act: 10.4731. Min Act: -0.1700
Data Index: 3730930 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4731. Min Range: -10.4731
Max Act: 10.2231. Min Act: -0.1700
Data Index: 1153017 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4731. Min Range: -10.4731
Max Act: 10.0356. Min Act: -0.1700
Data Index: 4694929 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4731. Min Range: -10.4731
Max Act: 10.0356. Min Act: -0.1700
Data Index: 7801076 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4731. Min Range: -10.4731
Max Act: 9.9731. Min Act: -0.1700
Data Index: 4620174 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4731. Min Range: -10.4731
Max Act: 9.9731. Min Act: -0.1700
Data Index: 3673205 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4731. Min Range: -10.4731
Max Act: 9.8481. Min Act: -0.1700
Data Index: 2839904 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4731. Min Range: -10.4731
Max Act: 9.8481. Min Act: -0.1700
Data Index: 570544 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4731. Min Range: -10.4731
Max Act: 9.7856. Min Act: -0.1700
Data Index: 4783009 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4731. Min Range: -10.4731
Max Act: 9.7856. Min Act: -0.1700
Data Index: 4981829 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4731. Min Range: -10.4731
Max Act: 9.7231. Min Act: -0.1700
Data Index: 6039075 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4731. Min Range: -10.4731
Max Act: 9.6606. Min Act: -0.1700
Data Index: 5077926 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4731. Min Range: -10.4731
Max Act: 9.5356. Min Act: -0.1700
Data Index: 8019965 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4731. Min Range: -10.4731
Max Act: 9.5981. Min Act: -0.1700
Data Index: 203996 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4731. Min Range: -10.4731
Max Act: 9.6606. Min Act: -0.1700
Data Index: 6881774 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4731. Min Range: -10.4731
Max Act: 9.5356. Min Act: -0.1700
Data Index: 3941341 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4731. Min Range: -10.4731
Max Act: 9.4731. Min Act: -0.1700
Data Index: 1795917 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4731. Min Range: -10.4731
Max Act: 9.4731. Min Act: -0.1700
Data Index: 7972228 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4731. Min Range: -10.4731
Max Act: 9.5356. Min Act: -0.1700
Data Index: 5232126 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4731. Min Range: -10.4731
Max Act: 9.4731. Min Act: -0.1700
Data Index: 2005098 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19