Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2824. Min Range: -3.2824
Max Act: 3.2824. Min Act: -0.1700
Data Index: 2050742 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2824. Min Range: -3.2824
Max Act: 3.2510. Min Act: -0.1700
Data Index: 447237 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2824. Min Range: -3.2824
Max Act: 3.2353. Min Act: -0.1700
Data Index: 4829494 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2824. Min Range: -3.2824
Max Act: 3.2353. Min Act: -0.1700
Data Index: 5244792 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2824. Min Range: -3.2824
Max Act: 3.2196. Min Act: -0.1700
Data Index: 4443898 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2824. Min Range: -3.2824
Max Act: 3.2039. Min Act: -0.1700
Data Index: 2062003 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2824. Min Range: -3.2824
Max Act: 3.2039. Min Act: -0.1700
Data Index: 2895787 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2824. Min Range: -3.2824
Max Act: 3.1881. Min Act: -0.1700
Data Index: 2895785 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2824. Min Range: -3.2824
Max Act: 3.2039. Min Act: -0.1700
Data Index: 6056986 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2824. Min Range: -3.2824
Max Act: 3.1881. Min Act: -0.1700
Data Index: 948694 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2824. Min Range: -3.2824
Max Act: 3.1881. Min Act: -0.1700
Data Index: 6029577 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2824. Min Range: -3.2824
Max Act: 3.1724. Min Act: -0.1700
Data Index: 5688984 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2824. Min Range: -3.2824
Max Act: 3.1567. Min Act: -0.1700
Data Index: 2593863 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2824. Min Range: -3.2824
Max Act: 3.1567. Min Act: -0.1700
Data Index: 5438845 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2824. Min Range: -3.2824
Max Act: 3.1409. Min Act: -0.1700
Data Index: 5309198 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2824. Min Range: -3.2824
Max Act: 3.1567. Min Act: -0.1700
Data Index: 5688985 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2824. Min Range: -3.2824
Max Act: 3.1409. Min Act: -0.1700
Data Index: 114928 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2824. Min Range: -3.2824
Max Act: 3.1409. Min Act: -0.1700
Data Index: 8647808 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2824. Min Range: -3.2824
Max Act: 3.1409. Min Act: -0.1700
Data Index: 862382 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2824. Min Range: -3.2824
Max Act: 3.1252. Min Act: -0.1700
Data Index: 8716334 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19