Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3308 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0800. Min Range: -8.0800
Max Act: 8.0800. Min Act: -0.1700
Data Index: 2542346 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0800. Min Range: -8.0800
Max Act: 8.0800. Min Act: -0.1700
Data Index: 1084869 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0800. Min Range: -8.0800
Max Act: 7.8925. Min Act: -0.1700
Data Index: 6048863 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0800. Min Range: -8.0800
Max Act: 7.8925. Min Act: -0.1700
Data Index: 5055814 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0800. Min Range: -8.0800
Max Act: 7.8925. Min Act: -0.1700
Data Index: 3816734 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0800. Min Range: -8.0800
Max Act: 7.8925. Min Act: -0.1700
Data Index: 5274412 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0800. Min Range: -8.0800
Max Act: 7.8925. Min Act: -0.1700
Data Index: 3599968 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0800. Min Range: -8.0800
Max Act: 7.8925. Min Act: -0.1700
Data Index: 1258074 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0800. Min Range: -8.0800
Max Act: 7.8925. Min Act: -0.1700
Data Index: 4601012 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0800. Min Range: -8.0800
Max Act: 7.8300. Min Act: -0.1700
Data Index: 1759798 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0800. Min Range: -8.0800
Max Act: 7.8300. Min Act: -0.1700
Data Index: 3884491 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0800. Min Range: -8.0800
Max Act: 7.7675. Min Act: -0.1700
Data Index: 1143072 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0800. Min Range: -8.0800
Max Act: 7.7050. Min Act: -0.1700
Data Index: 5508979 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0800. Min Range: -8.0800
Max Act: 7.7675. Min Act: -0.1700
Data Index: 2233986 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0800. Min Range: -8.0800
Max Act: 7.7050. Min Act: -0.1700
Data Index: 4552972 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0800. Min Range: -8.0800
Max Act: 7.7050. Min Act: -0.1700
Data Index: 7796140 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0800. Min Range: -8.0800
Max Act: 7.6425. Min Act: -0.1700
Data Index: 3757371 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0800. Min Range: -8.0800
Max Act: 7.7050. Min Act: -0.1700
Data Index: 5380378 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0800. Min Range: -8.0800
Max Act: 7.6425. Min Act: -0.1700
Data Index: 1593831 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0800. Min Range: -8.0800
Max Act: 7.6425. Min Act: -0.1700
Data Index: 959971 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19