Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2817 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0861. Min Range: -5.0861
Max Act: 5.0861. Min Act: -0.1700
Data Index: 2654351 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0861. Min Range: -5.0861
Max Act: 4.9924. Min Act: -0.1700
Data Index: 1960679 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0861. Min Range: -5.0861
Max Act: 4.9611. Min Act: -0.1700
Data Index: 6278610 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0861. Min Range: -5.0861
Max Act: 4.8986. Min Act: -0.1700
Data Index: 7953773 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0861. Min Range: -5.0861
Max Act: 4.8674. Min Act: -0.1700
Data Index: 4392032 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0861. Min Range: -5.0861
Max Act: 4.8986. Min Act: -0.1700
Data Index: 979946 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0861. Min Range: -5.0861
Max Act: 4.8674. Min Act: -0.1700
Data Index: 7868163 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0861. Min Range: -5.0861
Max Act: 4.8361. Min Act: -0.1700
Data Index: 2344939 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0861. Min Range: -5.0861
Max Act: 4.8361. Min Act: -0.1700
Data Index: 5794518 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0861. Min Range: -5.0861
Max Act: 4.8361. Min Act: -0.1700
Data Index: 605353 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0861. Min Range: -5.0861
Max Act: 4.8361. Min Act: -0.1700
Data Index: 8373357 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0861. Min Range: -5.0861
Max Act: 4.8049. Min Act: -0.1700
Data Index: 590845 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0861. Min Range: -5.0861
Max Act: 4.8049. Min Act: -0.1700
Data Index: 3465517 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0861. Min Range: -5.0861
Max Act: 4.7736. Min Act: -0.1700
Data Index: 3606881 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0861. Min Range: -5.0861
Max Act: 4.7424. Min Act: -0.1700
Data Index: 3014478 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0861. Min Range: -5.0861
Max Act: 4.7736. Min Act: -0.1700
Data Index: 1895669 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0861. Min Range: -5.0861
Max Act: 4.7736. Min Act: -0.1700
Data Index: 7374210 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0861. Min Range: -5.0861
Max Act: 4.7736. Min Act: -0.1700
Data Index: 7170866 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0861. Min Range: -5.0861
Max Act: 4.7736. Min Act: -0.1700
Data Index: 727956 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0861. Min Range: -5.0861
Max Act: 4.7424. Min Act: -0.1700
Data Index: 4100390 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19