Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5210 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.7603. Min Act: -0.1700
Data Index: 6360725 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.6353. Min Act: -0.1700
Data Index: 1166802 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.6978. Min Act: -0.1700
Data Index: 6893518 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.6353. Min Act: -0.1700
Data Index: 4117015 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.6040. Min Act: -0.1700
Data Index: 5779276 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.5728. Min Act: -0.1700
Data Index: 1591863 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.6040. Min Act: -0.1700
Data Index: 1166800 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.6040. Min Act: -0.1700
Data Index: 6360739 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.6040. Min Act: -0.1700
Data Index: 5392105 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.5728. Min Act: -0.1700
Data Index: 6462425 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.5728. Min Act: -0.1700
Data Index: 3444438 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.5415. Min Act: -0.1700
Data Index: 91486 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.5103. Min Act: -0.1700
Data Index: 2600770 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.4790. Min Act: -0.1700
Data Index: 861570 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.4790. Min Act: -0.1700
Data Index: 5443587 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.4790. Min Act: -0.1700
Data Index: 5443599 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.4790. Min Act: -0.1700
Data Index: 5444392 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.4790. Min Act: -0.1700
Data Index: 6307462 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.4790. Min Act: -0.1700
Data Index: 7402199 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.4478. Min Act: -0.1700
Data Index: 5779284 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19