Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3728 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6418. Min Range: -8.6418
Max Act: 8.6418. Min Act: -0.1700
Data Index: 2569852 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6418. Min Range: -8.6418
Max Act: 8.5793. Min Act: -0.1700
Data Index: 6557388 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6418. Min Range: -8.6418
Max Act: 8.5793. Min Act: -0.1700
Data Index: 8259055 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6418. Min Range: -8.6418
Max Act: 8.3293. Min Act: -0.1700
Data Index: 5027882 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6418. Min Range: -8.6418
Max Act: 8.2668. Min Act: -0.1700
Data Index: 6133185 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6418. Min Range: -8.6418
Max Act: 8.2668. Min Act: -0.1700
Data Index: 8694307 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6418. Min Range: -8.6418
Max Act: 8.2043. Min Act: -0.1700
Data Index: 989100 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6418. Min Range: -8.6418
Max Act: 8.2043. Min Act: -0.1700
Data Index: 5763629 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6418. Min Range: -8.6418
Max Act: 8.1418. Min Act: -0.1700
Data Index: 13960 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6418. Min Range: -8.6418
Max Act: 8.1418. Min Act: -0.1700
Data Index: 3712169 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6418. Min Range: -8.6418
Max Act: 8.0793. Min Act: -0.1700
Data Index: 2155150 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6418. Min Range: -8.6418
Max Act: 8.0793. Min Act: -0.1700
Data Index: 7494051 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6418. Min Range: -8.6418
Max Act: 8.0168. Min Act: -0.1700
Data Index: 4937751 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6418. Min Range: -8.6418
Max Act: 8.0168. Min Act: -0.1700
Data Index: 7629175 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6418. Min Range: -8.6418
Max Act: 8.0793. Min Act: -0.1700
Data Index: 5854227 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6418. Min Range: -8.6418
Max Act: 7.9543. Min Act: -0.1700
Data Index: 3461632 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6418. Min Range: -8.6418
Max Act: 7.8918. Min Act: -0.1700
Data Index: 393989 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6418. Min Range: -8.6418
Max Act: 7.8918. Min Act: -0.1700
Data Index: 6570011 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6418. Min Range: -8.6418
Max Act: 7.8918. Min Act: -0.1700
Data Index: 6222960 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6418. Min Range: -8.6418
Max Act: 7.8918. Min Act: -0.1700
Data Index: 7437025 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19