Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3034 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.2853. Min Act: -0.1700
Data Index: 8750211 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.2539. Min Act: -0.1700
Data Index: 6604598 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.2539. Min Act: -0.1700
Data Index: 1766889 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.2539. Min Act: -0.1700
Data Index: 5258577 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.2539. Min Act: -0.1700
Data Index: 5427773 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.2539. Min Act: -0.1700
Data Index: 3416534 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.2381. Min Act: -0.1700
Data Index: 5084016 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.2381. Min Act: -0.1700
Data Index: 1744216 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.2381. Min Act: -0.1700
Data Index: 566968 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.2381. Min Act: -0.1700
Data Index: 2125166 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.2224. Min Act: -0.1700
Data Index: 6273265 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.2381. Min Act: -0.1700
Data Index: 3443485 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.2381. Min Act: -0.1700
Data Index: 7130061 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.2381. Min Act: -0.1700
Data Index: 8192028 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.2224. Min Act: -0.1700
Data Index: 972884 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.2224. Min Act: -0.1700
Data Index: 7093163 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.2381. Min Act: -0.1700
Data Index: 7816784 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.2381. Min Act: -0.1700
Data Index: 937242 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.2381. Min Act: -0.1700
Data Index: 6971926 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.2381. Min Act: -0.1700
Data Index: 4345867 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19