Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 25 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.2867. Min Act: -0.1700
Data Index: 1850029 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.2867. Min Act: -0.1700
Data Index: 7017595 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.2242. Min Act: -0.1700
Data Index: 6126378 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0680. Min Act: -0.1700
Data Index: 5749201 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.9742. Min Act: -0.1700
Data Index: 6509776 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0055. Min Act: -0.1700
Data Index: 8584806 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0055. Min Act: -0.1700
Data Index: 2604601 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0055. Min Act: -0.1700
Data Index: 72850 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.9742. Min Act: -0.1700
Data Index: 3997675 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.9742. Min Act: -0.1700
Data Index: 4947433 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.9742. Min Act: -0.1700
Data Index: 4671337 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.9430. Min Act: -0.1700
Data Index: 7978388 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.9430. Min Act: -0.1700
Data Index: 5048547 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.9117. Min Act: -0.1700
Data Index: 3792764 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.8805. Min Act: -0.1700
Data Index: 3627747 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.9117. Min Act: -0.1700
Data Index: 6981649 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.8492. Min Act: -0.1700
Data Index: 7618320 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.8805. Min Act: -0.1700
Data Index: 5517837 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.8805. Min Act: -0.1700
Data Index: 2681017 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2867. Min Range: -5.2867
Max Act: 4.8805. Min Act: -0.1700
Data Index: 4455778 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19