Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2115 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.7693. Min Act: -0.1700
Data Index: 1303021 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.6755. Min Act: -0.1700
Data Index: 2010594 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.6130. Min Act: -0.1700
Data Index: 2733667 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.5505. Min Act: -0.1700
Data Index: 4619364 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.5505. Min Act: -0.1700
Data Index: 5138855 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.4880. Min Act: -0.1700
Data Index: 2207890 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.4568. Min Act: -0.1700
Data Index: 5022013 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.4568. Min Act: -0.1700
Data Index: 3801154 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.3943. Min Act: -0.1700
Data Index: 8604650 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.3318. Min Act: -0.1700
Data Index: 3349070 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.2380. Min Act: -0.1700
Data Index: 1056234 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.2068. Min Act: -0.1700
Data Index: 4612990 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.2068. Min Act: -0.1700
Data Index: 3607718 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.2068. Min Act: -0.1700
Data Index: 6489791 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.2068. Min Act: -0.1700
Data Index: 7264445 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.2068. Min Act: -0.1700
Data Index: 125838 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.1130. Min Act: -0.1700
Data Index: 3781485 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.0818. Min Act: -0.1700
Data Index: 74138 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.1130. Min Act: -0.1700
Data Index: 2045907 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.1130. Min Act: -0.1700
Data Index: 8787453 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19