Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2270 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3043. Min Range: -9.3043
Max Act: 9.3043. Min Act: -0.1700
Data Index: 2109128 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3043. Min Range: -9.3043
Max Act: 8.8668. Min Act: -0.1700
Data Index: 4470808 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3043. Min Range: -9.3043
Max Act: 8.6793. Min Act: -0.1700
Data Index: 8466997 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3043. Min Range: -9.3043
Max Act: 8.6168. Min Act: -0.1700
Data Index: 7163252 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3043. Min Range: -9.3043
Max Act: 8.5543. Min Act: -0.1700
Data Index: 6979141 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3043. Min Range: -9.3043
Max Act: 8.6168. Min Act: -0.1700
Data Index: 3386619 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3043. Min Range: -9.3043
Max Act: 8.5543. Min Act: -0.1700
Data Index: 467852 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3043. Min Range: -9.3043
Max Act: 8.5543. Min Act: -0.1700
Data Index: 4583475 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3043. Min Range: -9.3043
Max Act: 8.5543. Min Act: -0.1700
Data Index: 8335908 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3043. Min Range: -9.3043
Max Act: 8.5543. Min Act: -0.1700
Data Index: 6334333 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3043. Min Range: -9.3043
Max Act: 8.4918. Min Act: -0.1700
Data Index: 2630597 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3043. Min Range: -9.3043
Max Act: 8.4918. Min Act: -0.1700
Data Index: 7164996 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3043. Min Range: -9.3043
Max Act: 8.4293. Min Act: -0.1700
Data Index: 2601317 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3043. Min Range: -9.3043
Max Act: 8.4293. Min Act: -0.1700
Data Index: 613944 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3043. Min Range: -9.3043
Max Act: 8.3668. Min Act: -0.1700
Data Index: 4371160 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3043. Min Range: -9.3043
Max Act: 8.3668. Min Act: -0.1700
Data Index: 7613370 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3043. Min Range: -9.3043
Max Act: 8.3668. Min Act: -0.1700
Data Index: 3675450 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3043. Min Range: -9.3043
Max Act: 8.3043. Min Act: -0.1700
Data Index: 5436648 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3043. Min Range: -9.3043
Max Act: 8.1793. Min Act: -0.1700
Data Index: 5644386 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3043. Min Range: -9.3043
Max Act: 8.2418. Min Act: -0.1700
Data Index: 4991920 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19