Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5303 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4735. Min Range: -7.4735
Max Act: 7.4735. Min Act: -0.1700
Data Index: 6276745 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4735. Min Range: -7.4735
Max Act: 7.0673. Min Act: -0.1700
Data Index: 117546 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4735. Min Range: -7.4735
Max Act: 7.0985. Min Act: -0.1700
Data Index: 903141 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4735. Min Range: -7.4735
Max Act: 7.0673. Min Act: -0.1700
Data Index: 797366 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4735. Min Range: -7.4735
Max Act: 7.0360. Min Act: -0.1700
Data Index: 8293335 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4735. Min Range: -7.4735
Max Act: 7.0360. Min Act: -0.1700
Data Index: 6400371 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4735. Min Range: -7.4735
Max Act: 6.9735. Min Act: -0.1700
Data Index: 4566702 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4735. Min Range: -7.4735
Max Act: 6.9110. Min Act: -0.1700
Data Index: 1852733 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4735. Min Range: -7.4735
Max Act: 6.9423. Min Act: -0.1700
Data Index: 8482479 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4735. Min Range: -7.4735
Max Act: 6.8798. Min Act: -0.1700
Data Index: 1324178 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4735. Min Range: -7.4735
Max Act: 6.8798. Min Act: -0.1700
Data Index: 2262028 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4735. Min Range: -7.4735
Max Act: 6.8485. Min Act: -0.1700
Data Index: 58786 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4735. Min Range: -7.4735
Max Act: 6.8485. Min Act: -0.1700
Data Index: 4790110 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4735. Min Range: -7.4735
Max Act: 6.8485. Min Act: -0.1700
Data Index: 3560529 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4735. Min Range: -7.4735
Max Act: 6.8173. Min Act: -0.1700
Data Index: 37605 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4735. Min Range: -7.4735
Max Act: 6.8173. Min Act: -0.1700
Data Index: 8228548 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4735. Min Range: -7.4735
Max Act: 6.8173. Min Act: -0.1700
Data Index: 5126531 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4735. Min Range: -7.4735
Max Act: 6.7860. Min Act: -0.1700
Data Index: 6208596 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4735. Min Range: -7.4735
Max Act: 6.7860. Min Act: -0.1700
Data Index: 3177996 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4735. Min Range: -7.4735
Max Act: 6.7860. Min Act: -0.1700
Data Index: 6605823 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19