Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2554 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1415. Min Range: -7.1415
Max Act: 7.1415. Min Act: -0.1700
Data Index: 1501289 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1415. Min Range: -7.1415
Max Act: 7.1103. Min Act: -0.1700
Data Index: 3228475 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1415. Min Range: -7.1415
Max Act: 7.1103. Min Act: -0.1700
Data Index: 7072689 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.9228. Min Act: -0.1700
Data Index: 3256067 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.8290. Min Act: -0.1700
Data Index: 6479150 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.8603. Min Act: -0.1700
Data Index: 3062338 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.7978. Min Act: -0.1700
Data Index: 3301329 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.7978. Min Act: -0.1700
Data Index: 6478925 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.7353. Min Act: -0.1700
Data Index: 443750 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.6728. Min Act: -0.1700
Data Index: 5613815 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.6728. Min Act: -0.1700
Data Index: 2315640 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.7040. Min Act: -0.1700
Data Index: 1851515 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.6728. Min Act: -0.1700
Data Index: 612516 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.6415. Min Act: -0.1700
Data Index: 5607039 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.6415. Min Act: -0.1700
Data Index: 749372 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.6415. Min Act: -0.1700
Data Index: 6056799 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.5790. Min Act: -0.1700
Data Index: 206887 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.6103. Min Act: -0.1700
Data Index: 2183571 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.6415. Min Act: -0.1700
Data Index: 8640417 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.6415. Min Act: -0.1700
Data Index: 2947155 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19