Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 41 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9717. Min Range: -9.9717
Max Act: 9.9717. Min Act: -0.1700
Data Index: 2631273 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9717. Min Range: -9.9717
Max Act: 9.6592. Min Act: -0.1700
Data Index: 3673953 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9717. Min Range: -9.9717
Max Act: 9.6592. Min Act: -0.1700
Data Index: 5487718 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9717. Min Range: -9.9717
Max Act: 9.5967. Min Act: -0.1700
Data Index: 1500661 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9717. Min Range: -9.9717
Max Act: 9.4717. Min Act: -0.1700
Data Index: 4899553 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9717. Min Range: -9.9717
Max Act: 9.4092. Min Act: -0.1700
Data Index: 2607009 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9717. Min Range: -9.9717
Max Act: 9.4092. Min Act: -0.1700
Data Index: 2302013 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9717. Min Range: -9.9717
Max Act: 9.4092. Min Act: -0.1700
Data Index: 4787137 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9717. Min Range: -9.9717
Max Act: 9.4092. Min Act: -0.1700
Data Index: 6165522 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9717. Min Range: -9.9717
Max Act: 9.2842. Min Act: -0.1700
Data Index: 2638235 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9717. Min Range: -9.9717
Max Act: 9.3467. Min Act: -0.1700
Data Index: 3520943 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9717. Min Range: -9.9717
Max Act: 9.3467. Min Act: -0.1700
Data Index: 2033440 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9717. Min Range: -9.9717
Max Act: 9.3467. Min Act: -0.1700
Data Index: 5699379 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9717. Min Range: -9.9717
Max Act: 9.2842. Min Act: -0.1700
Data Index: 188680 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9717. Min Range: -9.9717
Max Act: 9.2842. Min Act: -0.1700
Data Index: 214121 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9717. Min Range: -9.9717
Max Act: 9.2842. Min Act: -0.1700
Data Index: 5548795 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9717. Min Range: -9.9717
Max Act: 9.1592. Min Act: -0.1700
Data Index: 1939704 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9717. Min Range: -9.9717
Max Act: 9.2217. Min Act: -0.1700
Data Index: 781950 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9717. Min Range: -9.9717
Max Act: 9.2217. Min Act: -0.1700
Data Index: 1273642 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9717. Min Range: -9.9717
Max Act: 9.1592. Min Act: -0.1700
Data Index: 5226663 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19