Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3791 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3718. Min Range: -6.3718
Max Act: 6.3718. Min Act: -0.1700
Data Index: 6861828 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3718. Min Range: -6.3718
Max Act: 6.3405. Min Act: -0.1700
Data Index: 2833609 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3718. Min Range: -6.3718
Max Act: 6.2155. Min Act: -0.1700
Data Index: 7164727 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3718. Min Range: -6.3718
Max Act: 6.1843. Min Act: -0.1700
Data Index: 8145211 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3718. Min Range: -6.3718
Max Act: 6.1530. Min Act: -0.1700
Data Index: 4799398 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3718. Min Range: -6.3718
Max Act: 6.1218. Min Act: -0.1700
Data Index: 3860454 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3718. Min Range: -6.3718
Max Act: 6.0905. Min Act: -0.1700
Data Index: 2463385 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3718. Min Range: -6.3718
Max Act: 6.0593. Min Act: -0.1700
Data Index: 5535729 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3718. Min Range: -6.3718
Max Act: 6.0280. Min Act: -0.1700
Data Index: 6296499 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3718. Min Range: -6.3718
Max Act: 6.0280. Min Act: -0.1700
Data Index: 204717 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3718. Min Range: -6.3718
Max Act: 6.0280. Min Act: -0.1700
Data Index: 3254821 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3718. Min Range: -6.3718
Max Act: 6.0280. Min Act: -0.1700
Data Index: 2785210 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3718. Min Range: -6.3718
Max Act: 5.9968. Min Act: -0.1700
Data Index: 822770 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3718. Min Range: -6.3718
Max Act: 5.9655. Min Act: -0.1700
Data Index: 8544864 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3718. Min Range: -6.3718
Max Act: 5.9968. Min Act: -0.1700
Data Index: 352233 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3718. Min Range: -6.3718
Max Act: 5.9968. Min Act: -0.1700
Data Index: 4112680 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3718. Min Range: -6.3718
Max Act: 5.9343. Min Act: -0.1700
Data Index: 1231466 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3718. Min Range: -6.3718
Max Act: 5.9030. Min Act: -0.1700
Data Index: 94070 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3718. Min Range: -6.3718
Max Act: 5.9030. Min Act: -0.1700
Data Index: 3711917 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3718. Min Range: -6.3718
Max Act: 5.9030. Min Act: -0.1700
Data Index: 1121584 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19