Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2993 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.3937. Min Act: -0.1700
Data Index: 2839676 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.3312. Min Act: -0.1700
Data Index: 594227 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.2374. Min Act: -0.1700
Data Index: 5414468 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.2374. Min Act: -0.1700
Data Index: 4736522 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.1749. Min Act: -0.1700
Data Index: 1515409 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.2062. Min Act: -0.1700
Data Index: 7130193 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.1749. Min Act: -0.1700
Data Index: 2767754 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.1749. Min Act: -0.1700
Data Index: 867858 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.1124. Min Act: -0.1700
Data Index: 8662380 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.1124. Min Act: -0.1700
Data Index: 2253407 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3937. Min Range: -6.3937
Max Act: 5.9562. Min Act: -0.1700
Data Index: 908322 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3937. Min Range: -6.3937
Max Act: 5.9562. Min Act: -0.1700
Data Index: 8249544 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3937. Min Range: -6.3937
Max Act: 5.8937. Min Act: -0.1700
Data Index: 7595079 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3937. Min Range: -6.3937
Max Act: 5.9249. Min Act: -0.1700
Data Index: 3626044 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3937. Min Range: -6.3937
Max Act: 5.8624. Min Act: -0.1700
Data Index: 8777782 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3937. Min Range: -6.3937
Max Act: 5.7999. Min Act: -0.1700
Data Index: 7351960 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3937. Min Range: -6.3937
Max Act: 5.7999. Min Act: -0.1700
Data Index: 2127880 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3937. Min Range: -6.3937
Max Act: 5.7687. Min Act: -0.1700
Data Index: 644428 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3937. Min Range: -6.3937
Max Act: 5.7687. Min Act: -0.1700
Data Index: 5268835 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3937. Min Range: -6.3937
Max Act: 5.7687. Min Act: -0.1700
Data Index: 2410062 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19