Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4575 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3779. Min Range: -6.3779
Max Act: 6.3779. Min Act: -0.1700
Data Index: 5944090 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3779. Min Range: -6.3779
Max Act: 6.1592. Min Act: -0.1700
Data Index: 5093485 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3779. Min Range: -6.3779
Max Act: 6.0967. Min Act: -0.1700
Data Index: 6247613 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3779. Min Range: -6.3779
Max Act: 6.0654. Min Act: -0.1700
Data Index: 7449541 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3779. Min Range: -6.3779
Max Act: 6.0654. Min Act: -0.1700
Data Index: 1400498 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3779. Min Range: -6.3779
Max Act: 6.0029. Min Act: -0.1700
Data Index: 5778720 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3779. Min Range: -6.3779
Max Act: 5.9404. Min Act: -0.1700
Data Index: 299737 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3779. Min Range: -6.3779
Max Act: 5.9404. Min Act: -0.1700
Data Index: 4918833 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3779. Min Range: -6.3779
Max Act: 5.9092. Min Act: -0.1700
Data Index: 8755245 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3779. Min Range: -6.3779
Max Act: 5.8779. Min Act: -0.1700
Data Index: 1123351 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3779. Min Range: -6.3779
Max Act: 5.9092. Min Act: -0.1700
Data Index: 5089688 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3779. Min Range: -6.3779
Max Act: 5.9092. Min Act: -0.1700
Data Index: 4409091 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3779. Min Range: -6.3779
Max Act: 5.9092. Min Act: -0.1700
Data Index: 8130285 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3779. Min Range: -6.3779
Max Act: 5.8467. Min Act: -0.1700
Data Index: 7206365 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3779. Min Range: -6.3779
Max Act: 5.8154. Min Act: -0.1700
Data Index: 3912649 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3779. Min Range: -6.3779
Max Act: 5.8154. Min Act: -0.1700
Data Index: 4124379 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3779. Min Range: -6.3779
Max Act: 5.7842. Min Act: -0.1700
Data Index: 417249 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3779. Min Range: -6.3779
Max Act: 5.7842. Min Act: -0.1700
Data Index: 811044 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3779. Min Range: -6.3779
Max Act: 5.7529. Min Act: -0.1700
Data Index: 2253660 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3779. Min Range: -6.3779
Max Act: 5.7842. Min Act: -0.1700
Data Index: 1786898 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19