Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2631 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7012. Min Range: -4.7012
Max Act: 4.7012. Min Act: -0.1700
Data Index: 2569950 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7012. Min Range: -4.7012
Max Act: 4.6699. Min Act: -0.1700
Data Index: 6746718 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7012. Min Range: -4.7012
Max Act: 4.6387. Min Act: -0.1700
Data Index: 5302890 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7012. Min Range: -4.7012
Max Act: 4.5762. Min Act: -0.1700
Data Index: 8285006 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7012. Min Range: -4.7012
Max Act: 4.5137. Min Act: -0.1700
Data Index: 2591156 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7012. Min Range: -4.7012
Max Act: 4.4824. Min Act: -0.1700
Data Index: 5497615 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7012. Min Range: -4.7012
Max Act: 4.4512. Min Act: -0.1700
Data Index: 5229550 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7012. Min Range: -4.7012
Max Act: 4.4512. Min Act: -0.1700
Data Index: 1690033 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7012. Min Range: -4.7012
Max Act: 4.3887. Min Act: -0.1700
Data Index: 8598212 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7012. Min Range: -4.7012
Max Act: 4.3887. Min Act: -0.1700
Data Index: 8656813 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7012. Min Range: -4.7012
Max Act: 4.3574. Min Act: -0.1700
Data Index: 3257150 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7012. Min Range: -4.7012
Max Act: 4.3887. Min Act: -0.1700
Data Index: 5790755 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7012. Min Range: -4.7012
Max Act: 4.3887. Min Act: -0.1700
Data Index: 8256118 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7012. Min Range: -4.7012
Max Act: 4.3262. Min Act: -0.1700
Data Index: 5158974 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7012. Min Range: -4.7012
Max Act: 4.3262. Min Act: -0.1700
Data Index: 2997928 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7012. Min Range: -4.7012
Max Act: 4.3262. Min Act: -0.1700
Data Index: 769782 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7012. Min Range: -4.7012
Max Act: 4.3574. Min Act: -0.1700
Data Index: 3505684 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7012. Min Range: -4.7012
Max Act: 4.3262. Min Act: -0.1700
Data Index: 3378210 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7012. Min Range: -4.7012
Max Act: 4.2949. Min Act: -0.1700
Data Index: 3224393 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7012. Min Range: -4.7012
Max Act: 4.2949. Min Act: -0.1700
Data Index: 824830 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19