Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 485 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6718. Min Range: -4.6718
Max Act: 4.6718. Min Act: -0.1700
Data Index: 6952246 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6718. Min Range: -4.6718
Max Act: 4.6405. Min Act: -0.1700
Data Index: 8207842 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6718. Min Range: -4.6718
Max Act: 4.6405. Min Act: -0.1700
Data Index: 1453858 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6718. Min Range: -4.6718
Max Act: 4.5780. Min Act: -0.1700
Data Index: 1453857 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6718. Min Range: -4.6718
Max Act: 4.5780. Min Act: -0.1700
Data Index: 7246477 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6718. Min Range: -4.6718
Max Act: 4.5780. Min Act: -0.1700
Data Index: 7391567 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6718. Min Range: -4.6718
Max Act: 4.5780. Min Act: -0.1700
Data Index: 3785351 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6718. Min Range: -4.6718
Max Act: 4.5468. Min Act: -0.1700
Data Index: 4927138 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6718. Min Range: -4.6718
Max Act: 4.4843. Min Act: -0.1700
Data Index: 5436679 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6718. Min Range: -4.6718
Max Act: 4.5155. Min Act: -0.1700
Data Index: 5300722 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6718. Min Range: -4.6718
Max Act: 4.4843. Min Act: -0.1700
Data Index: 5536768 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6718. Min Range: -4.6718
Max Act: 4.5155. Min Act: -0.1700
Data Index: 2305418 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6718. Min Range: -4.6718
Max Act: 4.4843. Min Act: -0.1700
Data Index: 8615657 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6718. Min Range: -4.6718
Max Act: 4.4843. Min Act: -0.1700
Data Index: 5648798 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6718. Min Range: -4.6718
Max Act: 4.4530. Min Act: -0.1700
Data Index: 8552087 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6718. Min Range: -4.6718
Max Act: 4.4530. Min Act: -0.1700
Data Index: 8615665 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6718. Min Range: -4.6718
Max Act: 4.4843. Min Act: -0.1700
Data Index: 232456 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6718. Min Range: -4.6718
Max Act: 4.4218. Min Act: -0.1700
Data Index: 289491 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6718. Min Range: -4.6718
Max Act: 4.3905. Min Act: -0.1700
Data Index: 6084309 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6718. Min Range: -4.6718
Max Act: 4.4218. Min Act: -0.1700
Data Index: 67035 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19