Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3068 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0516. Min Range: -5.0516
Max Act: 5.0516. Min Act: -0.1700
Data Index: 8697444 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.9891. Min Act: -0.1700
Data Index: 3138095 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.9578. Min Act: -0.1700
Data Index: 4177586 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.9578. Min Act: -0.1700
Data Index: 912426 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.9578. Min Act: -0.1700
Data Index: 5690285 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8953. Min Act: -0.1700
Data Index: 5959855 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8641. Min Act: -0.1700
Data Index: 1194635 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8641. Min Act: -0.1700
Data Index: 4102788 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8328. Min Act: -0.1700
Data Index: 5716640 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8328. Min Act: -0.1700
Data Index: 8298787 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8328. Min Act: -0.1700
Data Index: 1044056 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8328. Min Act: -0.1700
Data Index: 5911790 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8328. Min Act: -0.1700
Data Index: 1249761 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8328. Min Act: -0.1700
Data Index: 3946359 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8641. Min Act: -0.1700
Data Index: 8665476 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8016. Min Act: -0.1700
Data Index: 575120 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8016. Min Act: -0.1700
Data Index: 4830262 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.8016. Min Act: -0.1700
Data Index: 4206273 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.7703. Min Act: -0.1700
Data Index: 8527529 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0516. Min Range: -5.0516
Max Act: 4.7703. Min Act: -0.1700
Data Index: 7587048 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19