Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5593 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2901. Min Range: -8.2901
Max Act: 8.2901. Min Act: -0.1700
Data Index: 6145067 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2901. Min Range: -8.2901
Max Act: 8.2276. Min Act: -0.1700
Data Index: 6964600 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2901. Min Range: -8.2901
Max Act: 8.1026. Min Act: -0.1700
Data Index: 1027846 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2901. Min Range: -8.2901
Max Act: 8.1651. Min Act: -0.1700
Data Index: 8622748 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2901. Min Range: -8.2901
Max Act: 8.0401. Min Act: -0.1700
Data Index: 7053880 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2901. Min Range: -8.2901
Max Act: 8.0401. Min Act: -0.1700
Data Index: 4801608 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2901. Min Range: -8.2901
Max Act: 8.0401. Min Act: -0.1700
Data Index: 5254552 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2901. Min Range: -8.2901
Max Act: 8.1026. Min Act: -0.1700
Data Index: 454260 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2901. Min Range: -8.2901
Max Act: 7.9776. Min Act: -0.1700
Data Index: 5262114 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2901. Min Range: -8.2901
Max Act: 7.9776. Min Act: -0.1700
Data Index: 2901280 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2901. Min Range: -8.2901
Max Act: 7.9776. Min Act: -0.1700
Data Index: 6425373 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2901. Min Range: -8.2901
Max Act: 7.9776. Min Act: -0.1700
Data Index: 5711270 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2901. Min Range: -8.2901
Max Act: 7.8526. Min Act: -0.1700
Data Index: 4765003 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2901. Min Range: -8.2901
Max Act: 7.8526. Min Act: -0.1700
Data Index: 2849382 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2901. Min Range: -8.2901
Max Act: 7.8526. Min Act: -0.1700
Data Index: 3850938 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2901. Min Range: -8.2901
Max Act: 7.7901. Min Act: -0.1700
Data Index: 3184121 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2901. Min Range: -8.2901
Max Act: 7.7901. Min Act: -0.1700
Data Index: 3608253 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2901. Min Range: -8.2901
Max Act: 7.7901. Min Act: -0.1700
Data Index: 3119999 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2901. Min Range: -8.2901
Max Act: 7.7901. Min Act: -0.1700
Data Index: 5248502 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2901. Min Range: -8.2901
Max Act: 7.7901. Min Act: -0.1700
Data Index: 922660 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19