Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3088 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0441. Min Range: -4.0441
Max Act: 4.0441. Min Act: -0.1700
Data Index: 3193355 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0441. Min Range: -4.0441
Max Act: 4.0441. Min Act: -0.1700
Data Index: 3924950 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0441. Min Range: -4.0441
Max Act: 3.9816. Min Act: -0.1700
Data Index: 5237561 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0441. Min Range: -4.0441
Max Act: 3.8878. Min Act: -0.1700
Data Index: 7164487 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0441. Min Range: -4.0441
Max Act: 3.8878. Min Act: -0.1700
Data Index: 1917073 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0441. Min Range: -4.0441
Max Act: 3.8878. Min Act: -0.1700
Data Index: 6026851 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0441. Min Range: -4.0441
Max Act: 3.8565. Min Act: -0.1700
Data Index: 1567436 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0441. Min Range: -4.0441
Max Act: 3.8565. Min Act: -0.1700
Data Index: 2957881 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0441. Min Range: -4.0441
Max Act: 3.8252. Min Act: -0.1700
Data Index: 3247289 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0441. Min Range: -4.0441
Max Act: 3.7940. Min Act: -0.1700
Data Index: 8039156 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0441. Min Range: -4.0441
Max Act: 3.8252. Min Act: -0.1700
Data Index: 2619338 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0441. Min Range: -4.0441
Max Act: 3.7940. Min Act: -0.1700
Data Index: 5879676 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0441. Min Range: -4.0441
Max Act: 3.7627. Min Act: -0.1700
Data Index: 8109734 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0441. Min Range: -4.0441
Max Act: 3.7627. Min Act: -0.1700
Data Index: 1420966 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0441. Min Range: -4.0441
Max Act: 3.7627. Min Act: -0.1700
Data Index: 7123763 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0441. Min Range: -4.0441
Max Act: 3.7314. Min Act: -0.1700
Data Index: 4180396 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0441. Min Range: -4.0441
Max Act: 3.7314. Min Act: -0.1700
Data Index: 6751261 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0441. Min Range: -4.0441
Max Act: 3.7314. Min Act: -0.1700
Data Index: 4782763 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0441. Min Range: -4.0441
Max Act: 3.7001. Min Act: -0.1700
Data Index: 7437943 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0441. Min Range: -4.0441
Max Act: 3.7001. Min Act: -0.1700
Data Index: 5005247 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19