Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2776 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2006. Min Range: -5.2006
Max Act: 5.2006. Min Act: -0.1700
Data Index: 8743088 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.8568. Min Act: -0.1700
Data Index: 3376405 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.7943. Min Act: -0.1700
Data Index: 5958748 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.7631. Min Act: -0.1700
Data Index: 2355240 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.6693. Min Act: -0.1700
Data Index: 3805602 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.6693. Min Act: -0.1700
Data Index: 3484765 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.6068. Min Act: -0.1700
Data Index: 2271237 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.6068. Min Act: -0.1700
Data Index: 6786392 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.5756. Min Act: -0.1700
Data Index: 946050 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.5756. Min Act: -0.1700
Data Index: 1158776 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.5756. Min Act: -0.1700
Data Index: 987482 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.5443. Min Act: -0.1700
Data Index: 5866054 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.5443. Min Act: -0.1700
Data Index: 5624447 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.5443. Min Act: -0.1700
Data Index: 7416032 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.5131. Min Act: -0.1700
Data Index: 5800176 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.5131. Min Act: -0.1700
Data Index: 3826913 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.5131. Min Act: -0.1700
Data Index: 7342949 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.5131. Min Act: -0.1700
Data Index: 7852201 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.5131. Min Act: -0.1700
Data Index: 1606016 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.5131. Min Act: -0.1700
Data Index: 7184569 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19