Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4410 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9662. Min Range: -3.9662
Max Act: 3.9662. Min Act: -0.1700
Data Index: 1414011 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9662. Min Range: -3.9662
Max Act: 3.8724. Min Act: -0.1700
Data Index: 4235196 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9662. Min Range: -3.9662
Max Act: 3.8724. Min Act: -0.1700
Data Index: 7523766 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9662. Min Range: -3.9662
Max Act: 3.8724. Min Act: -0.1700
Data Index: 3785459 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9662. Min Range: -3.9662
Max Act: 3.8724. Min Act: -0.1700
Data Index: 1393849 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9662. Min Range: -3.9662
Max Act: 3.8412. Min Act: -0.1700
Data Index: 1228525 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9662. Min Range: -3.9662
Max Act: 3.8724. Min Act: -0.1700
Data Index: 7543415 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9662. Min Range: -3.9662
Max Act: 3.8099. Min Act: -0.1700
Data Index: 258859 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9662. Min Range: -3.9662
Max Act: 3.8099. Min Act: -0.1700
Data Index: 4488159 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9662. Min Range: -3.9662
Max Act: 3.8412. Min Act: -0.1699
Data Index: 1676775 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9662. Min Range: -3.9662
Max Act: 3.8099. Min Act: -0.1700
Data Index: 3415134 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9662. Min Range: -3.9662
Max Act: 3.8099. Min Act: -0.1696
Data Index: 787209 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9662. Min Range: -3.9662
Max Act: 3.8099. Min Act: -0.1699
Data Index: 6304488 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9662. Min Range: -3.9662
Max Act: 3.8099. Min Act: -0.1700
Data Index: 4827793 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9662. Min Range: -3.9662
Max Act: 3.7786. Min Act: -0.1700
Data Index: 1393850 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9662. Min Range: -3.9662
Max Act: 3.7786. Min Act: -0.1700
Data Index: 1154391 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9662. Min Range: -3.9662
Max Act: 3.7473. Min Act: -0.1700
Data Index: 3660170 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9662. Min Range: -3.9662
Max Act: 3.7473. Min Act: -0.1700
Data Index: 1154386 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9662. Min Range: -3.9662
Max Act: 3.7473. Min Act: -0.1698
Data Index: 1693409 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9662. Min Range: -3.9662
Max Act: 3.7473. Min Act: -0.1687
Data Index: 1749664 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19