Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.9542. Min Act: -0.1700
Data Index: 8351446 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.9230. Min Act: -0.1700
Data Index: 3795837 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.8917. Min Act: -0.1700
Data Index: 738151 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.8605. Min Act: -0.1700
Data Index: 2402845 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.8605. Min Act: -0.1700
Data Index: 2431329 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.8292. Min Act: -0.1700
Data Index: 1491714 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.8605. Min Act: -0.1700
Data Index: 3610717 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.8292. Min Act: -0.1700
Data Index: 2631767 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.8292. Min Act: -0.1700
Data Index: 6375735 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.7979. Min Act: -0.1700
Data Index: 7494365 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.8292. Min Act: -0.1700
Data Index: 8021984 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.7979. Min Act: -0.1700
Data Index: 1380831 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.7354. Min Act: -0.1700
Data Index: 3610735 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.7666. Min Act: -0.1700
Data Index: 746131 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.7666. Min Act: -0.1700
Data Index: 7227594 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.7666. Min Act: -0.1700
Data Index: 2633129 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.7666. Min Act: -0.1700
Data Index: 4899188 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.7666. Min Act: -0.1700
Data Index: 2378781 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.7666. Min Act: -0.1700
Data Index: 5849388 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.7666. Min Act: -0.1700
Data Index: 782847 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19