Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2650 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5690. Min Range: -4.5690
Max Act: 4.5690. Min Act: -0.1700
Data Index: 517261 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5690. Min Range: -4.5690
Max Act: 4.4440. Min Act: -0.1700
Data Index: 6295642 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5690. Min Range: -4.5690
Max Act: 4.4127. Min Act: -0.1700
Data Index: 2393932 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5690. Min Range: -4.5690
Max Act: 4.3190. Min Act: -0.1700
Data Index: 6190620 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5690. Min Range: -4.5690
Max Act: 4.2565. Min Act: -0.1700
Data Index: 8350064 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5690. Min Range: -4.5690
Max Act: 4.2565. Min Act: -0.1700
Data Index: 4919478 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5690. Min Range: -4.5690
Max Act: 4.2252. Min Act: -0.1700
Data Index: 5303309 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5690. Min Range: -4.5690
Max Act: 4.1940. Min Act: -0.1700
Data Index: 457653 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5690. Min Range: -4.5690
Max Act: 4.1627. Min Act: -0.1700
Data Index: 2046841 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5690. Min Range: -4.5690
Max Act: 4.1627. Min Act: -0.1700
Data Index: 7683689 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5690. Min Range: -4.5690
Max Act: 4.1627. Min Act: -0.1700
Data Index: 7029293 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5690. Min Range: -4.5690
Max Act: 4.1627. Min Act: -0.1700
Data Index: 2279288 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5690. Min Range: -4.5690
Max Act: 4.1315. Min Act: -0.1700
Data Index: 8069801 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5690. Min Range: -4.5690
Max Act: 4.1315. Min Act: -0.1700
Data Index: 1526921 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5690. Min Range: -4.5690
Max Act: 4.1315. Min Act: -0.1700
Data Index: 5223812 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5690. Min Range: -4.5690
Max Act: 4.1315. Min Act: -0.1700
Data Index: 7019712 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5690. Min Range: -4.5690
Max Act: 4.0690. Min Act: -0.1700
Data Index: 3712364 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5690. Min Range: -4.5690
Max Act: 4.0690. Min Act: -0.1700
Data Index: 6693989 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5690. Min Range: -4.5690
Max Act: 4.0690. Min Act: -0.1700
Data Index: 6715113 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5690. Min Range: -4.5690
Max Act: 4.0690. Min Act: -0.1700
Data Index: 2918157 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19