Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3273 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3309. Min Range: -3.3309
Max Act: 3.3309. Min Act: -0.1700
Data Index: 2666133 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3309. Min Range: -3.3309
Max Act: 3.3152. Min Act: -0.1700
Data Index: 7197669 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3309. Min Range: -3.3309
Max Act: 3.3152. Min Act: -0.1700
Data Index: 2415776 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3309. Min Range: -3.3309
Max Act: 3.2995. Min Act: -0.1700
Data Index: 8832492 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3309. Min Range: -3.3309
Max Act: 3.2995. Min Act: -0.1700
Data Index: 5006260 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3309. Min Range: -3.3309
Max Act: 3.2838. Min Act: -0.1700
Data Index: 5583432 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3309. Min Range: -3.3309
Max Act: 3.2838. Min Act: -0.1700
Data Index: 4704575 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3309. Min Range: -3.3309
Max Act: 3.2995. Min Act: -0.1700
Data Index: 5958849 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3309. Min Range: -3.3309
Max Act: 3.2681. Min Act: -0.1700
Data Index: 8419869 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3309. Min Range: -3.3309
Max Act: 3.2681. Min Act: -0.1700
Data Index: 1495082 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3309. Min Range: -3.3309
Max Act: 3.2681. Min Act: -0.1700
Data Index: 4945329 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3309. Min Range: -3.3309
Max Act: 3.2681. Min Act: -0.1700
Data Index: 5921716 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3309. Min Range: -3.3309
Max Act: 3.2524. Min Act: -0.1700
Data Index: 6453565 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3309. Min Range: -3.3309
Max Act: 3.2524. Min Act: -0.1700
Data Index: 256981 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3309. Min Range: -3.3309
Max Act: 3.2524. Min Act: -0.1700
Data Index: 6406276 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3309. Min Range: -3.3309
Max Act: 3.2524. Min Act: -0.1700
Data Index: 4794518 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3309. Min Range: -3.3309
Max Act: 3.2524. Min Act: -0.1700
Data Index: 4221779 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3309. Min Range: -3.3309
Max Act: 3.2524. Min Act: -0.1700
Data Index: 7510335 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3309. Min Range: -3.3309
Max Act: 3.2367. Min Act: -0.1700
Data Index: 202652 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3309. Min Range: -3.3309
Max Act: 3.2367. Min Act: -0.1700
Data Index: 7223968 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19