Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 634 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9250. Min Range: -3.9250
Max Act: 3.9250. Min Act: -0.1700
Data Index: 4613957 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9250. Min Range: -3.9250
Max Act: 3.5809. Min Act: -0.1700
Data Index: 8595980 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9250. Min Range: -3.9250
Max Act: 3.5496. Min Act: -0.1700
Data Index: 2247711 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9250. Min Range: -3.9250
Max Act: 3.5340. Min Act: -0.1700
Data Index: 4083623 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9250. Min Range: -3.9250
Max Act: 3.5340. Min Act: -0.1700
Data Index: 6238872 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9250. Min Range: -3.9250
Max Act: 3.5027. Min Act: -0.1700
Data Index: 3999982 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9250. Min Range: -3.9250
Max Act: 3.3616. Min Act: -0.1700
Data Index: 508522 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9250. Min Range: -3.9250
Max Act: 3.3145. Min Act: -0.1700
Data Index: 1925926 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9250. Min Range: -3.9250
Max Act: 3.2988. Min Act: -0.1700
Data Index: 6320619 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9250. Min Range: -3.9250
Max Act: 3.2831. Min Act: -0.1700
Data Index: 1276316 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9250. Min Range: -3.9250
Max Act: 3.2831. Min Act: -0.1700
Data Index: 3839488 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9250. Min Range: -3.9250
Max Act: 3.2674. Min Act: -0.1700
Data Index: 3264059 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9250. Min Range: -3.9250
Max Act: 3.2360. Min Act: -0.1700
Data Index: 2218209 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9250. Min Range: -3.9250
Max Act: 3.2360. Min Act: -0.1700
Data Index: 6696426 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9250. Min Range: -3.9250
Max Act: 3.2203. Min Act: -0.1700
Data Index: 400979 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9250. Min Range: -3.9250
Max Act: 3.2203. Min Act: -0.1700
Data Index: 1856288 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9250. Min Range: -3.9250
Max Act: 3.2046. Min Act: -0.1700
Data Index: 1829972 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9250. Min Range: -3.9250
Max Act: 3.2046. Min Act: -0.1700
Data Index: 4241780 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9250. Min Range: -3.9250
Max Act: 3.2046. Min Act: -0.1700
Data Index: 4569029 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9250. Min Range: -3.9250
Max Act: 3.1888. Min Act: -0.1700
Data Index: 5283075 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19