Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3061 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7428. Min Range: -5.7428
Max Act: 5.7428. Min Act: -0.1700
Data Index: 3347262 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7428. Min Range: -5.7428
Max Act: 5.6803. Min Act: -0.1700
Data Index: 5405061 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7428. Min Range: -5.7428
Max Act: 5.5865. Min Act: -0.1700
Data Index: 5972862 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7428. Min Range: -5.7428
Max Act: 5.5240. Min Act: -0.1700
Data Index: 8742000 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7428. Min Range: -5.7428
Max Act: 5.5240. Min Act: -0.1700
Data Index: 1388426 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7428. Min Range: -5.7428
Max Act: 5.5240. Min Act: -0.1700
Data Index: 643984 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7428. Min Range: -5.7428
Max Act: 5.4928. Min Act: -0.1700
Data Index: 16319 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7428. Min Range: -5.7428
Max Act: 5.4615. Min Act: -0.1700
Data Index: 2203137 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7428. Min Range: -5.7428
Max Act: 5.4615. Min Act: -0.1700
Data Index: 2425310 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7428. Min Range: -5.7428
Max Act: 5.4303. Min Act: -0.1700
Data Index: 1270096 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7428. Min Range: -5.7428
Max Act: 5.4615. Min Act: -0.1700
Data Index: 5453460 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7428. Min Range: -5.7428
Max Act: 5.4303. Min Act: -0.1700
Data Index: 6422937 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7428. Min Range: -5.7428
Max Act: 5.4303. Min Act: -0.1700
Data Index: 298734 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7428. Min Range: -5.7428
Max Act: 5.3678. Min Act: -0.1700
Data Index: 7490645 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7428. Min Range: -5.7428
Max Act: 5.3678. Min Act: -0.1700
Data Index: 493797 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7428. Min Range: -5.7428
Max Act: 5.3678. Min Act: -0.1700
Data Index: 3139481 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7428. Min Range: -5.7428
Max Act: 5.3678. Min Act: -0.1700
Data Index: 6811270 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7428. Min Range: -5.7428
Max Act: 5.3365. Min Act: -0.1700
Data Index: 5412713 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7428. Min Range: -5.7428
Max Act: 5.3365. Min Act: -0.1700
Data Index: 1717541 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7428. Min Range: -5.7428
Max Act: 5.3365. Min Act: -0.1700
Data Index: 2202753 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #19