Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2718 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9269. Min Range: -0.9269
Max Act: 0.9269. Min Act: -0.1700
Data Index: 7758989 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9269. Min Range: -0.9269
Max Act: 0.9183. Min Act: -0.1700
Data Index: 7085281 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9269. Min Range: -0.9269
Max Act: 0.9269. Min Act: -0.1700
Data Index: 5785053 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9269. Min Range: -0.9269
Max Act: 0.9097. Min Act: -0.1700
Data Index: 6204077 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9269. Min Range: -0.9269
Max Act: 0.8926. Min Act: -0.1700
Data Index: 6269246 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9269. Min Range: -0.9269
Max Act: 0.9097. Min Act: -0.1700
Data Index: 8750984 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9269. Min Range: -0.9269
Max Act: 0.9011. Min Act: -0.1700
Data Index: 2104773 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9269. Min Range: -0.9269
Max Act: 0.8926. Min Act: -0.1700
Data Index: 4409842 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9269. Min Range: -0.9269
Max Act: 0.8755. Min Act: -0.1700
Data Index: 4933990 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9269. Min Range: -0.9269
Max Act: 0.8840. Min Act: -0.1700
Data Index: 2011123 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9269. Min Range: -0.9269
Max Act: 0.8755. Min Act: -0.1700
Data Index: 3696560 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9269. Min Range: -0.9269
Max Act: 0.8755. Min Act: -0.1700
Data Index: 3518527 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9269. Min Range: -0.9269
Max Act: 0.8755. Min Act: -0.1700
Data Index: 7747097 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9269. Min Range: -0.9269
Max Act: 0.8670. Min Act: -0.1700
Data Index: 8310178 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9269. Min Range: -0.9269
Max Act: 0.8755. Min Act: -0.1700
Data Index: 2519290 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9269. Min Range: -0.9269
Max Act: 0.8755. Min Act: -0.1700
Data Index: 1392538 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9269. Min Range: -0.9269
Max Act: 0.8755. Min Act: -0.1700
Data Index: 777690 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9269. Min Range: -0.9269
Max Act: 0.8755. Min Act: -0.1700
Data Index: 1743088 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9269. Min Range: -0.9269
Max Act: 0.8755. Min Act: -0.1700
Data Index: 6458552 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9269. Min Range: -0.9269
Max Act: 0.8670. Min Act: -0.1700
Data Index: 4392039 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19