Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2385 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.2355. Min Act: -0.1700
Data Index: 2353909 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.1730. Min Act: -0.1700
Data Index: 706457 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.1730. Min Act: -0.1700
Data Index: 4468310 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.1730. Min Act: -0.1700
Data Index: 35951 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.1417. Min Act: -0.1700
Data Index: 3420863 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.1417. Min Act: -0.1700
Data Index: 5061948 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.1417. Min Act: -0.1700
Data Index: 2826685 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.1417. Min Act: -0.1700
Data Index: 2470590 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.1417. Min Act: -0.1700
Data Index: 2078851 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.1417. Min Act: -0.1700
Data Index: 3801103 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.1417. Min Act: -0.1700
Data Index: 3795373 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.1105. Min Act: -0.1700
Data Index: 4033481 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.1417. Min Act: -0.1700
Data Index: 4174298 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.1105. Min Act: -0.1700
Data Index: 4390941 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.1105. Min Act: -0.1700
Data Index: 3925523 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.1105. Min Act: -0.1700
Data Index: 1786921 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.1105. Min Act: -0.1700
Data Index: 4996404 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.1105. Min Act: -0.1700
Data Index: 2610577 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.1417. Min Act: -0.1700
Data Index: 857989 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.1105. Min Act: -0.1700
Data Index: 788165 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19