Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1299 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9818. Min Range: -4.9818
Max Act: 4.9818. Min Act: -0.1700
Data Index: 4048968 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9818. Min Range: -4.9818
Max Act: 4.9818. Min Act: -0.1700
Data Index: 8099085 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9818. Min Range: -4.9818
Max Act: 4.9506. Min Act: -0.1700
Data Index: 653370 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9818. Min Range: -4.9818
Max Act: 4.9818. Min Act: -0.1700
Data Index: 3395830 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9818. Min Range: -4.9818
Max Act: 4.9506. Min Act: -0.1700
Data Index: 5663975 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9818. Min Range: -4.9818
Max Act: 4.9506. Min Act: -0.1700
Data Index: 3592835 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9818. Min Range: -4.9818
Max Act: 4.9506. Min Act: -0.1700
Data Index: 1306505 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9818. Min Range: -4.9818
Max Act: 4.9193. Min Act: -0.1700
Data Index: 1952830 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9818. Min Range: -4.9818
Max Act: 4.9193. Min Act: -0.1700
Data Index: 2675817 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9818. Min Range: -4.9818
Max Act: 4.9193. Min Act: -0.1700
Data Index: 7951619 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9818. Min Range: -4.9818
Max Act: 4.9193. Min Act: -0.1700
Data Index: 6752174 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9818. Min Range: -4.9818
Max Act: 4.9193. Min Act: -0.1700
Data Index: 3036696 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9818. Min Range: -4.9818
Max Act: 4.8881. Min Act: -0.1700
Data Index: 2651034 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9818. Min Range: -4.9818
Max Act: 4.8881. Min Act: -0.1700
Data Index: 4232972 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9818. Min Range: -4.9818
Max Act: 4.8568. Min Act: -0.1700
Data Index: 6876161 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9818. Min Range: -4.9818
Max Act: 4.8568. Min Act: -0.1700
Data Index: 1868830 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9818. Min Range: -4.9818
Max Act: 4.8568. Min Act: -0.1700
Data Index: 5984949 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9818. Min Range: -4.9818
Max Act: 4.8256. Min Act: -0.1700
Data Index: 5912089 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9818. Min Range: -4.9818
Max Act: 4.8256. Min Act: -0.1700
Data Index: 2889089 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9818. Min Range: -4.9818
Max Act: 4.8256. Min Act: -0.1700
Data Index: 4732326 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19