Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6205 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0719. Min Range: -3.0719
Max Act: 3.0719. Min Act: -0.1700
Data Index: 2078754 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0719. Min Range: -3.0719
Max Act: 3.0087. Min Act: -0.1700
Data Index: 7639206 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0719. Min Range: -3.0719
Max Act: 2.8503. Min Act: -0.1700
Data Index: 3411771 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0719. Min Range: -3.0719
Max Act: 2.8344. Min Act: -0.1700
Data Index: 6979108 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0719. Min Range: -3.0719
Max Act: 2.7867. Min Act: -0.1700
Data Index: 8350254 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0719. Min Range: -3.0719
Max Act: 2.7707. Min Act: -0.1700
Data Index: 1887620 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0719. Min Range: -3.0719
Max Act: 2.7707. Min Act: -0.1700
Data Index: 2514691 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0719. Min Range: -3.0719
Max Act: 2.7707. Min Act: -0.1700
Data Index: 2222864 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0719. Min Range: -3.0719
Max Act: 2.7548. Min Act: -0.1700
Data Index: 1580794 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0719. Min Range: -3.0719
Max Act: 2.7548. Min Act: -0.1700
Data Index: 2183001 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0719. Min Range: -3.0719
Max Act: 2.7548. Min Act: -0.1700
Data Index: 5528805 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0719. Min Range: -3.0719
Max Act: 2.7388. Min Act: -0.1700
Data Index: 8032877 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0719. Min Range: -3.0719
Max Act: 2.7388. Min Act: -0.1700
Data Index: 5727894 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0719. Min Range: -3.0719
Max Act: 2.7228. Min Act: -0.1700
Data Index: 4434355 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0719. Min Range: -3.0719
Max Act: 2.7228. Min Act: -0.1700
Data Index: 7646183 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0719. Min Range: -3.0719
Max Act: 2.6909. Min Act: -0.1700
Data Index: 6795532 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0719. Min Range: -3.0719
Max Act: 2.6909. Min Act: -0.1700
Data Index: 505544 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0719. Min Range: -3.0719
Max Act: 2.6428. Min Act: -0.1700
Data Index: 3019039 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0719. Min Range: -3.0719
Max Act: 2.6588. Min Act: -0.1700
Data Index: 7079778 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0719. Min Range: -3.0719
Max Act: 2.6428. Min Act: -0.1700
Data Index: 7236887 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19