Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3836 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9027. Min Range: -5.9027
Max Act: 5.9027. Min Act: -0.1700
Data Index: 4618015 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9027. Min Range: -5.9027
Max Act: 5.7152. Min Act: -0.1700
Data Index: 8115725 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9027. Min Range: -5.9027
Max Act: 5.7152. Min Act: -0.1700
Data Index: 3670846 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9027. Min Range: -5.9027
Max Act: 5.7152. Min Act: -0.1700
Data Index: 6597635 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9027. Min Range: -5.9027
Max Act: 5.6527. Min Act: -0.1700
Data Index: 4312576 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9027. Min Range: -5.9027
Max Act: 5.5902. Min Act: -0.1700
Data Index: 8310054 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9027. Min Range: -5.9027
Max Act: 5.5902. Min Act: -0.1700
Data Index: 8694023 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9027. Min Range: -5.9027
Max Act: 5.5589. Min Act: -0.1700
Data Index: 620829 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9027. Min Range: -5.9027
Max Act: 5.5589. Min Act: -0.1700
Data Index: 5575543 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9027. Min Range: -5.9027
Max Act: 5.5589. Min Act: -0.1700
Data Index: 4386040 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9027. Min Range: -5.9027
Max Act: 5.5277. Min Act: -0.1700
Data Index: 1442623 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9027. Min Range: -5.9027
Max Act: 5.5589. Min Act: -0.1700
Data Index: 395234 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9027. Min Range: -5.9027
Max Act: 5.4652. Min Act: -0.1700
Data Index: 6689811 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9027. Min Range: -5.9027
Max Act: 5.4964. Min Act: -0.1700
Data Index: 4219626 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9027. Min Range: -5.9027
Max Act: 5.4964. Min Act: -0.1700
Data Index: 5734835 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9027. Min Range: -5.9027
Max Act: 5.4964. Min Act: -0.1700
Data Index: 5396376 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9027. Min Range: -5.9027
Max Act: 5.4964. Min Act: -0.1700
Data Index: 7364877 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9027. Min Range: -5.9027
Max Act: 5.4964. Min Act: -0.1700
Data Index: 3613790 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9027. Min Range: -5.9027
Max Act: 5.4652. Min Act: -0.1700
Data Index: 1075393 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9027. Min Range: -5.9027
Max Act: 5.4964. Min Act: -0.1700
Data Index: 7373330 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19