Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4705 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2724. Min Range: -5.2724
Max Act: 5.2724. Min Act: -0.1700
Data Index: 2697750 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2724. Min Range: -5.2724
Max Act: 5.2724. Min Act: -0.1700
Data Index: 2616684 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2724. Min Range: -5.2724
Max Act: 5.2411. Min Act: -0.1700
Data Index: 472549 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2724. Min Range: -5.2724
Max Act: 5.2099. Min Act: -0.1700
Data Index: 4068516 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2724. Min Range: -5.2724
Max Act: 5.1786. Min Act: -0.1700
Data Index: 3557669 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2724. Min Range: -5.2724
Max Act: 5.1474. Min Act: -0.1700
Data Index: 5228936 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2724. Min Range: -5.2724
Max Act: 5.1474. Min Act: -0.1700
Data Index: 7027371 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2724. Min Range: -5.2724
Max Act: 5.0849. Min Act: -0.1700
Data Index: 1894422 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2724. Min Range: -5.2724
Max Act: 5.1161. Min Act: -0.1700
Data Index: 5084006 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2724. Min Range: -5.2724
Max Act: 5.1161. Min Act: -0.1700
Data Index: 8641050 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2724. Min Range: -5.2724
Max Act: 5.0849. Min Act: -0.1700
Data Index: 7496054 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2724. Min Range: -5.2724
Max Act: 5.0849. Min Act: -0.1700
Data Index: 7496055 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2724. Min Range: -5.2724
Max Act: 5.0849. Min Act: -0.1700
Data Index: 1329557 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2724. Min Range: -5.2724
Max Act: 5.0849. Min Act: -0.1700
Data Index: 6204755 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2724. Min Range: -5.2724
Max Act: 5.0849. Min Act: -0.1700
Data Index: 3386486 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2724. Min Range: -5.2724
Max Act: 5.1161. Min Act: -0.1700
Data Index: 1232353 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2724. Min Range: -5.2724
Max Act: 5.0849. Min Act: -0.1700
Data Index: 7902629 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2724. Min Range: -5.2724
Max Act: 5.0849. Min Act: -0.1700
Data Index: 1154051 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2724. Min Range: -5.2724
Max Act: 5.0536. Min Act: -0.1700
Data Index: 4525624 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2724. Min Range: -5.2724
Max Act: 5.0536. Min Act: -0.1700
Data Index: 4833446 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19