Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3312 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5637. Min Range: -8.5637
Max Act: 8.5637. Min Act: -0.1700
Data Index: 5372058 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5637. Min Range: -8.5637
Max Act: 8.2512. Min Act: -0.1700
Data Index: 4221686 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5637. Min Range: -8.5637
Max Act: 8.1262. Min Act: -0.1700
Data Index: 7050834 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5637. Min Range: -8.5637
Max Act: 8.0324. Min Act: -0.1700
Data Index: 1146133 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5637. Min Range: -8.5637
Max Act: 7.9387. Min Act: -0.1700
Data Index: 895084 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5637. Min Range: -8.5637
Max Act: 7.7512. Min Act: -0.1700
Data Index: 921906 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5637. Min Range: -8.5637
Max Act: 7.6887. Min Act: -0.1700
Data Index: 7750049 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5637. Min Range: -8.5637
Max Act: 7.6574. Min Act: -0.1700
Data Index: 5716572 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5637. Min Range: -8.5637
Max Act: 7.6574. Min Act: -0.1700
Data Index: 829215 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5637. Min Range: -8.5637
Max Act: 7.6574. Min Act: -0.1700
Data Index: 5081730 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5637. Min Range: -8.5637
Max Act: 7.6262. Min Act: -0.1700
Data Index: 2682243 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5637. Min Range: -8.5637
Max Act: 7.6574. Min Act: -0.1700
Data Index: 2458852 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5637. Min Range: -8.5637
Max Act: 7.5949. Min Act: -0.1700
Data Index: 3204515 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5637. Min Range: -8.5637
Max Act: 7.5949. Min Act: -0.1700
Data Index: 6480104 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5637. Min Range: -8.5637
Max Act: 7.5637. Min Act: -0.1700
Data Index: 3712479 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5637. Min Range: -8.5637
Max Act: 7.5012. Min Act: -0.1700
Data Index: 2179746 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5637. Min Range: -8.5637
Max Act: 7.5012. Min Act: -0.1700
Data Index: 7863673 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5637. Min Range: -8.5637
Max Act: 7.4387. Min Act: -0.1700
Data Index: 8626472 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5637. Min Range: -8.5637
Max Act: 7.4074. Min Act: -0.1700
Data Index: 7867122 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5637. Min Range: -8.5637
Max Act: 7.4074. Min Act: -0.1700
Data Index: 4268778 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19