Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5098 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.2926. Min Act: -0.1700
Data Index: 3495756 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.2926. Min Act: -0.1700
Data Index: 659599 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1676. Min Act: -0.1700
Data Index: 7594735 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1051. Min Act: -0.1700
Data Index: 3846447 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1364. Min Act: -0.1700
Data Index: 6126702 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1051. Min Act: -0.1700
Data Index: 3093400 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.0738. Min Act: -0.1700
Data Index: 4755449 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.0426. Min Act: -0.1700
Data Index: 5969791 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.0426. Min Act: -0.1700
Data Index: 1063367 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.0113. Min Act: -0.1700
Data Index: 6986133 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.0113. Min Act: -0.1700
Data Index: 6382046 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2926. Min Range: -4.2926
Max Act: 3.9801. Min Act: -0.1700
Data Index: 2828135 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.0113. Min Act: -0.1700
Data Index: 6051963 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2926. Min Range: -4.2926
Max Act: 3.9801. Min Act: -0.1700
Data Index: 2427981 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2926. Min Range: -4.2926
Max Act: 3.9801. Min Act: -0.1700
Data Index: 5452229 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2926. Min Range: -4.2926
Max Act: 3.9488. Min Act: -0.1700
Data Index: 5015815 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2926. Min Range: -4.2926
Max Act: 3.9801. Min Act: -0.1700
Data Index: 3428963 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2926. Min Range: -4.2926
Max Act: 3.9801. Min Act: -0.1700
Data Index: 6382836 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2926. Min Range: -4.2926
Max Act: 3.9488. Min Act: -0.1700
Data Index: 7961030 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2926. Min Range: -4.2926
Max Act: 3.9801. Min Act: -0.1700
Data Index: 1332916 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19