Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 665 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2812. Min Range: -7.2812
Max Act: 7.2812. Min Act: -0.1700
Data Index: 4791789 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2812. Min Range: -7.2812
Max Act: 7.1250. Min Act: -0.1700
Data Index: 6367373 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2812. Min Range: -7.2812
Max Act: 7.0000. Min Act: -0.1700
Data Index: 4113849 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2812. Min Range: -7.2812
Max Act: 6.9375. Min Act: -0.1700
Data Index: 5595175 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2812. Min Range: -7.2812
Max Act: 6.8750. Min Act: -0.1700
Data Index: 1523001 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2812. Min Range: -7.2812
Max Act: 6.8437. Min Act: -0.1700
Data Index: 4887135 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2812. Min Range: -7.2812
Max Act: 6.7812. Min Act: -0.1700
Data Index: 7750800 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2812. Min Range: -7.2812
Max Act: 6.8437. Min Act: -0.1700
Data Index: 1772404 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2812. Min Range: -7.2812
Max Act: 6.8437. Min Act: -0.1700
Data Index: 4316057 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2812. Min Range: -7.2812
Max Act: 6.8125. Min Act: -0.1700
Data Index: 2069592 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2812. Min Range: -7.2812
Max Act: 6.7187. Min Act: -0.1700
Data Index: 3373671 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2812. Min Range: -7.2812
Max Act: 6.6875. Min Act: -0.1700
Data Index: 3096265 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2812. Min Range: -7.2812
Max Act: 6.6875. Min Act: -0.1700
Data Index: 7827940 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2812. Min Range: -7.2812
Max Act: 6.6875. Min Act: -0.1700
Data Index: 3816596 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2812. Min Range: -7.2812
Max Act: 6.6562. Min Act: -0.1700
Data Index: 1790739 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2812. Min Range: -7.2812
Max Act: 6.6562. Min Act: -0.1700
Data Index: 5850143 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2812. Min Range: -7.2812
Max Act: 6.6562. Min Act: -0.1700
Data Index: 2722238 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2812. Min Range: -7.2812
Max Act: 6.6562. Min Act: -0.1700
Data Index: 3732360 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2812. Min Range: -7.2812
Max Act: 6.6562. Min Act: -0.1700
Data Index: 4010925 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2812. Min Range: -7.2812
Max Act: 6.5937. Min Act: -0.1700
Data Index: 3031535 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19