Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3746 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8369. Min Range: -8.8369
Max Act: 8.8369. Min Act: -0.1700
Data Index: 2095700 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8369. Min Range: -8.8369
Max Act: 8.7119. Min Act: -0.1700
Data Index: 4395180 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8369. Min Range: -8.8369
Max Act: 8.7119. Min Act: -0.1700
Data Index: 451776 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8369. Min Range: -8.8369
Max Act: 8.3994. Min Act: -0.1700
Data Index: 6674570 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8369. Min Range: -8.8369
Max Act: 8.3994. Min Act: -0.1700
Data Index: 3422477 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8369. Min Range: -8.8369
Max Act: 8.3369. Min Act: -0.1700
Data Index: 4291627 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8369. Min Range: -8.8369
Max Act: 8.3369. Min Act: -0.1700
Data Index: 5430931 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8369. Min Range: -8.8369
Max Act: 8.3369. Min Act: -0.1700
Data Index: 3678700 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8369. Min Range: -8.8369
Max Act: 8.3369. Min Act: -0.1700
Data Index: 1938703 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8369. Min Range: -8.8369
Max Act: 8.2744. Min Act: -0.1700
Data Index: 5358142 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8369. Min Range: -8.8369
Max Act: 8.2744. Min Act: -0.1700
Data Index: 3755090 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8369. Min Range: -8.8369
Max Act: 8.2744. Min Act: -0.1700
Data Index: 3069915 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8369. Min Range: -8.8369
Max Act: 8.2119. Min Act: -0.1700
Data Index: 5111918 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8369. Min Range: -8.8369
Max Act: 8.2119. Min Act: -0.1700
Data Index: 5500610 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8369. Min Range: -8.8369
Max Act: 8.2119. Min Act: -0.1700
Data Index: 6929606 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8369. Min Range: -8.8369
Max Act: 8.2119. Min Act: -0.1700
Data Index: 8538953 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8369. Min Range: -8.8369
Max Act: 8.1494. Min Act: -0.1700
Data Index: 1541842 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8369. Min Range: -8.8369
Max Act: 8.1494. Min Act: -0.1700
Data Index: 2410916 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8369. Min Range: -8.8369
Max Act: 8.2119. Min Act: -0.1700
Data Index: 2317131 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8369. Min Range: -8.8369
Max Act: 8.1494. Min Act: -0.1700
Data Index: 5628106 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19