Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2530 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0888. Min Range: -6.0888
Max Act: 6.0888. Min Act: -0.1700
Data Index: 1257973 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0888. Min Range: -6.0888
Max Act: 5.7450. Min Act: -0.1700
Data Index: 5614668 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0888. Min Range: -6.0888
Max Act: 5.7450. Min Act: -0.1700
Data Index: 3371707 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0888. Min Range: -6.0888
Max Act: 5.7450. Min Act: -0.1699
Data Index: 1574226 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0888. Min Range: -6.0888
Max Act: 5.7138. Min Act: -0.1700
Data Index: 7538556 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0888. Min Range: -6.0888
Max Act: 5.6825. Min Act: -0.1700
Data Index: 726243 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0888. Min Range: -6.0888
Max Act: 5.6825. Min Act: -0.1700
Data Index: 3672407 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0888. Min Range: -6.0888
Max Act: 5.6825. Min Act: -0.1700
Data Index: 4392883 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0888. Min Range: -6.0888
Max Act: 5.6513. Min Act: -0.1700
Data Index: 2757327 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0888. Min Range: -6.0888
Max Act: 5.6513. Min Act: -0.1700
Data Index: 1980774 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0888. Min Range: -6.0888
Max Act: 5.6200. Min Act: -0.1700
Data Index: 7271447 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0888. Min Range: -6.0888
Max Act: 5.6200. Min Act: -0.1700
Data Index: 4692769 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0888. Min Range: -6.0888
Max Act: 5.6200. Min Act: -0.1700
Data Index: 3889576 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0888. Min Range: -6.0888
Max Act: 5.6200. Min Act: -0.1700
Data Index: 7936646 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0888. Min Range: -6.0888
Max Act: 5.5888. Min Act: -0.1700
Data Index: 5221048 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0888. Min Range: -6.0888
Max Act: 5.5888. Min Act: -0.1700
Data Index: 5215977 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0888. Min Range: -6.0888
Max Act: 5.5888. Min Act: -0.1700
Data Index: 995794 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0888. Min Range: -6.0888
Max Act: 5.5888. Min Act: -0.1700
Data Index: 5171836 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0888. Min Range: -6.0888
Max Act: 5.5575. Min Act: -0.1700
Data Index: 1691248 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0888. Min Range: -6.0888
Max Act: 5.5575. Min Act: -0.1700
Data Index: 1980775 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19