Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5047 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3996. Min Range: -5.3996
Max Act: 5.3996. Min Act: -0.1700
Data Index: 6329698 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3996. Min Range: -5.3996
Max Act: 5.3371. Min Act: -0.1700
Data Index: 7910144 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3996. Min Range: -5.3996
Max Act: 5.3371. Min Act: -0.1700
Data Index: 21885 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3996. Min Range: -5.3996
Max Act: 5.3058. Min Act: -0.1700
Data Index: 3548111 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3996. Min Range: -5.3996
Max Act: 5.2746. Min Act: -0.1700
Data Index: 5801544 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3996. Min Range: -5.3996
Max Act: 5.2746. Min Act: -0.1700
Data Index: 6658906 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3996. Min Range: -5.3996
Max Act: 5.2746. Min Act: -0.1700
Data Index: 3104977 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3996. Min Range: -5.3996
Max Act: 5.2433. Min Act: -0.1700
Data Index: 134079 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3996. Min Range: -5.3996
Max Act: 5.2121. Min Act: -0.1700
Data Index: 1154550 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3996. Min Range: -5.3996
Max Act: 5.2121. Min Act: -0.1700
Data Index: 4116522 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3996. Min Range: -5.3996
Max Act: 5.2121. Min Act: -0.1700
Data Index: 5672848 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3996. Min Range: -5.3996
Max Act: 5.2121. Min Act: -0.1700
Data Index: 951698 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3996. Min Range: -5.3996
Max Act: 5.2121. Min Act: -0.1700
Data Index: 8164893 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3996. Min Range: -5.3996
Max Act: 5.2121. Min Act: -0.1700
Data Index: 3539521 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3996. Min Range: -5.3996
Max Act: 5.1808. Min Act: -0.1700
Data Index: 951699 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3996. Min Range: -5.3996
Max Act: 5.1808. Min Act: -0.1700
Data Index: 3087764 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3996. Min Range: -5.3996
Max Act: 5.2121. Min Act: -0.1700
Data Index: 2659007 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3996. Min Range: -5.3996
Max Act: 5.1496. Min Act: -0.1700
Data Index: 7385353 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3996. Min Range: -5.3996
Max Act: 5.1808. Min Act: -0.1700
Data Index: 1761531 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3996. Min Range: -5.3996
Max Act: 5.1808. Min Act: -0.1700
Data Index: 1128874 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19