Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 675 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2363. Min Range: -5.2363
Max Act: 5.2363. Min Act: -0.1700
Data Index: 8634241 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2363. Min Range: -5.2363
Max Act: 5.1113. Min Act: -0.1700
Data Index: 2915052 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2363. Min Range: -5.2363
Max Act: 5.0800. Min Act: -0.1700
Data Index: 7071060 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2363. Min Range: -5.2363
Max Act: 5.0800. Min Act: -0.1700
Data Index: 3621955 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2363. Min Range: -5.2363
Max Act: 5.0800. Min Act: -0.1700
Data Index: 1959821 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2363. Min Range: -5.2363
Max Act: 5.0800. Min Act: -0.1700
Data Index: 7791924 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2363. Min Range: -5.2363
Max Act: 4.9863. Min Act: -0.1700
Data Index: 4014942 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2363. Min Range: -5.2363
Max Act: 4.8925. Min Act: -0.1700
Data Index: 1813918 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2363. Min Range: -5.2363
Max Act: 4.8925. Min Act: -0.1700
Data Index: 4603795 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2363. Min Range: -5.2363
Max Act: 4.8613. Min Act: -0.1700
Data Index: 468042 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2363. Min Range: -5.2363
Max Act: 4.8300. Min Act: -0.1700
Data Index: 1024029 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2363. Min Range: -5.2363
Max Act: 4.8300. Min Act: -0.1700
Data Index: 152893 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2363. Min Range: -5.2363
Max Act: 4.8613. Min Act: -0.1700
Data Index: 3504828 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2363. Min Range: -5.2363
Max Act: 4.8300. Min Act: -0.1700
Data Index: 5244039 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2363. Min Range: -5.2363
Max Act: 4.7988. Min Act: -0.1700
Data Index: 3598812 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2363. Min Range: -5.2363
Max Act: 4.7988. Min Act: -0.1700
Data Index: 6277666 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2363. Min Range: -5.2363
Max Act: 4.7988. Min Act: -0.1700
Data Index: 2752714 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2363. Min Range: -5.2363
Max Act: 4.7988. Min Act: -0.1700
Data Index: 730488 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2363. Min Range: -5.2363
Max Act: 4.7675. Min Act: -0.1700
Data Index: 1911832 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2363. Min Range: -5.2363
Max Act: 4.7675. Min Act: -0.1700
Data Index: 8438233 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19