Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3998 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9440. Min Range: -6.9440
Max Act: 6.9440. Min Act: -0.1700
Data Index: 8551326 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9440. Min Range: -6.9440
Max Act: 6.8503. Min Act: -0.1700
Data Index: 6208904 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9440. Min Range: -6.9440
Max Act: 6.8190. Min Act: -0.1700
Data Index: 2223722 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9440. Min Range: -6.9440
Max Act: 6.7878. Min Act: -0.1700
Data Index: 935569 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9440. Min Range: -6.9440
Max Act: 6.7253. Min Act: -0.1700
Data Index: 5802023 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9440. Min Range: -6.9440
Max Act: 6.7253. Min Act: -0.1700
Data Index: 4410588 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9440. Min Range: -6.9440
Max Act: 6.7253. Min Act: -0.1700
Data Index: 2690144 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9440. Min Range: -6.9440
Max Act: 6.6315. Min Act: -0.1700
Data Index: 2038703 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9440. Min Range: -6.9440
Max Act: 6.6003. Min Act: -0.1700
Data Index: 7814174 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9440. Min Range: -6.9440
Max Act: 6.5065. Min Act: -0.1700
Data Index: 4531747 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9440. Min Range: -6.9440
Max Act: 6.4128. Min Act: -0.1700
Data Index: 1376776 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9440. Min Range: -6.9440
Max Act: 6.4440. Min Act: -0.1700
Data Index: 172376 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9440. Min Range: -6.9440
Max Act: 6.4128. Min Act: -0.1700
Data Index: 3428673 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9440. Min Range: -6.9440
Max Act: 6.3815. Min Act: -0.1700
Data Index: 6117005 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9440. Min Range: -6.9440
Max Act: 6.3815. Min Act: -0.1700
Data Index: 3167904 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9440. Min Range: -6.9440
Max Act: 6.3815. Min Act: -0.1700
Data Index: 5281086 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9440. Min Range: -6.9440
Max Act: 6.3815. Min Act: -0.1700
Data Index: 2147478 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9440. Min Range: -6.9440
Max Act: 6.3190. Min Act: -0.1700
Data Index: 1415684 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9440. Min Range: -6.9440
Max Act: 6.2565. Min Act: -0.1700
Data Index: 7420086 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9440. Min Range: -6.9440
Max Act: 6.2878. Min Act: -0.1700
Data Index: 5032408 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19