Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3001 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0724. Min Range: -4.0724
Max Act: 4.0724. Min Act: -0.1700
Data Index: 4054411 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0724. Min Range: -4.0724
Max Act: 4.0411. Min Act: -0.1700
Data Index: 2538819 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0724. Min Range: -4.0724
Max Act: 4.0724. Min Act: -0.1700
Data Index: 7451524 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0724. Min Range: -4.0724
Max Act: 3.9786. Min Act: -0.1700
Data Index: 4432651 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0724. Min Range: -4.0724
Max Act: 3.9786. Min Act: -0.1700
Data Index: 5313863 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0724. Min Range: -4.0724
Max Act: 4.0099. Min Act: -0.1700
Data Index: 3109368 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0724. Min Range: -4.0724
Max Act: 3.9786. Min Act: -0.1700
Data Index: 3337010 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0724. Min Range: -4.0724
Max Act: 3.9473. Min Act: -0.1700
Data Index: 5031198 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0724. Min Range: -4.0724
Max Act: 3.9473. Min Act: -0.1700
Data Index: 6268777 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0724. Min Range: -4.0724
Max Act: 3.9161. Min Act: -0.1700
Data Index: 7656286 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0724. Min Range: -4.0724
Max Act: 3.9161. Min Act: -0.1700
Data Index: 3928320 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0724. Min Range: -4.0724
Max Act: 3.9161. Min Act: -0.1700
Data Index: 6666396 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0724. Min Range: -4.0724
Max Act: 3.8848. Min Act: -0.1700
Data Index: 2538815 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0724. Min Range: -4.0724
Max Act: 3.8535. Min Act: -0.1700
Data Index: 2538820 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0724. Min Range: -4.0724
Max Act: 3.8535. Min Act: -0.1700
Data Index: 7844654 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0724. Min Range: -4.0724
Max Act: 3.8535. Min Act: -0.1700
Data Index: 5931259 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0724. Min Range: -4.0724
Max Act: 3.8223. Min Act: -0.1700
Data Index: 2538816 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0724. Min Range: -4.0724
Max Act: 3.8223. Min Act: -0.1700
Data Index: 4054413 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0724. Min Range: -4.0724
Max Act: 3.8223. Min Act: -0.1700
Data Index: 7311309 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0724. Min Range: -4.0724
Max Act: 3.7910. Min Act: -0.1700
Data Index: 1060351 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19