Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4098 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5920. Min Range: -6.5920
Max Act: 6.5920. Min Act: -0.1700
Data Index: 5635314 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5920. Min Range: -6.5920
Max Act: 6.5295. Min Act: -0.1700
Data Index: 3387074 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5920. Min Range: -6.5920
Max Act: 6.5295. Min Act: -0.1700
Data Index: 6367997 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5920. Min Range: -6.5920
Max Act: 6.5295. Min Act: -0.1700
Data Index: 3900854 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5920. Min Range: -6.5920
Max Act: 6.5295. Min Act: -0.1700
Data Index: 1262877 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5920. Min Range: -6.5920
Max Act: 6.5295. Min Act: -0.1700
Data Index: 1759660 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5920. Min Range: -6.5920
Max Act: 6.4670. Min Act: -0.1700
Data Index: 3522485 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5920. Min Range: -6.5920
Max Act: 6.4983. Min Act: -0.1700
Data Index: 1799053 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5920. Min Range: -6.5920
Max Act: 6.4983. Min Act: -0.1700
Data Index: 8058231 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5920. Min Range: -6.5920
Max Act: 6.4983. Min Act: -0.1700
Data Index: 7607985 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5920. Min Range: -6.5920
Max Act: 6.4670. Min Act: -0.1700
Data Index: 2868687 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5920. Min Range: -6.5920
Max Act: 6.4670. Min Act: -0.1700
Data Index: 2058372 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5920. Min Range: -6.5920
Max Act: 6.4670. Min Act: -0.1700
Data Index: 2031956 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5920. Min Range: -6.5920
Max Act: 6.4670. Min Act: -0.1700
Data Index: 4338958 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5920. Min Range: -6.5920
Max Act: 6.4670. Min Act: -0.1700
Data Index: 103076 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5920. Min Range: -6.5920
Max Act: 6.4670. Min Act: -0.1700
Data Index: 454588 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5920. Min Range: -6.5920
Max Act: 6.4670. Min Act: -0.1700
Data Index: 3618378 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5920. Min Range: -6.5920
Max Act: 6.4358. Min Act: -0.1700
Data Index: 7003538 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5920. Min Range: -6.5920
Max Act: 6.4358. Min Act: -0.1700
Data Index: 1877640 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5920. Min Range: -6.5920
Max Act: 6.4358. Min Act: -0.1700
Data Index: 4381010 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19