Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1684 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3066. Min Range: -4.3066
Max Act: 4.3066. Min Act: -0.1700
Data Index: 7256591 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3066. Min Range: -4.3066
Max Act: 3.8846. Min Act: -0.1700
Data Index: 4829396 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3066. Min Range: -4.3066
Max Act: 3.7908. Min Act: -0.1700
Data Index: 8334178 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3066. Min Range: -4.3066
Max Act: 3.8221. Min Act: -0.1700
Data Index: 188228 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3066. Min Range: -4.3066
Max Act: 3.7752. Min Act: -0.1700
Data Index: 4118053 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3066. Min Range: -4.3066
Max Act: 3.7439. Min Act: -0.1700
Data Index: 8681542 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3066. Min Range: -4.3066
Max Act: 3.7283. Min Act: -0.1700
Data Index: 3693592 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3066. Min Range: -4.3066
Max Act: 3.7283. Min Act: -0.1700
Data Index: 8431879 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3066. Min Range: -4.3066
Max Act: 3.7126. Min Act: -0.1700
Data Index: 5904725 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3066. Min Range: -4.3066
Max Act: 3.6814. Min Act: -0.1700
Data Index: 5719364 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3066. Min Range: -4.3066
Max Act: 3.6814. Min Act: -0.1700
Data Index: 7355326 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3066. Min Range: -4.3066
Max Act: 3.6657. Min Act: -0.1700
Data Index: 6828582 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3066. Min Range: -4.3066
Max Act: 3.6814. Min Act: -0.1700
Data Index: 8058208 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3066. Min Range: -4.3066
Max Act: 3.6501. Min Act: -0.1700
Data Index: 7608088 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3066. Min Range: -4.3066
Max Act: 3.6188. Min Act: -0.1700
Data Index: 5286865 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3066. Min Range: -4.3066
Max Act: 3.6344. Min Act: -0.1700
Data Index: 3539404 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3066. Min Range: -4.3066
Max Act: 3.5875. Min Act: -0.1700
Data Index: 2638992 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3066. Min Range: -4.3066
Max Act: 3.5875. Min Act: -0.1700
Data Index: 5839842 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3066. Min Range: -4.3066
Max Act: 3.5718. Min Act: -0.1700
Data Index: 5653644 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3066. Min Range: -4.3066
Max Act: 3.5718. Min Act: -0.1700
Data Index: 2886872 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19