Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 753 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5300. Min Range: -3.5300
Max Act: 3.5300. Min Act: -0.1700
Data Index: 5778168 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5300. Min Range: -3.5300
Max Act: 3.5300. Min Act: -0.1700
Data Index: 5366384 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5300. Min Range: -3.5300
Max Act: 3.5300. Min Act: -0.1700
Data Index: 2787696 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5300. Min Range: -3.5300
Max Act: 3.5300. Min Act: -0.1700
Data Index: 1624103 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5300. Min Range: -3.5300
Max Act: 3.5300. Min Act: -0.1700
Data Index: 6158373 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5300. Min Range: -3.5300
Max Act: 3.4987. Min Act: -0.1700
Data Index: 664011 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5300. Min Range: -3.5300
Max Act: 3.4987. Min Act: -0.1700
Data Index: 5907587 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5300. Min Range: -3.5300
Max Act: 3.4987. Min Act: -0.1700
Data Index: 7961934 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5300. Min Range: -3.5300
Max Act: 3.4987. Min Act: -0.1700
Data Index: 3794776 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5300. Min Range: -3.5300
Max Act: 3.4987. Min Act: -0.1700
Data Index: 5733780 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5300. Min Range: -3.5300
Max Act: 3.4674. Min Act: -0.1700
Data Index: 3441586 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5300. Min Range: -3.5300
Max Act: 3.4674. Min Act: -0.1700
Data Index: 386566 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5300. Min Range: -3.5300
Max Act: 3.4674. Min Act: -0.1700
Data Index: 3700563 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5300. Min Range: -3.5300
Max Act: 3.4674. Min Act: -0.1700
Data Index: 1489193 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5300. Min Range: -3.5300
Max Act: 3.4360. Min Act: -0.1700
Data Index: 2257851 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5300. Min Range: -3.5300
Max Act: 3.4360. Min Act: -0.1700
Data Index: 1216563 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5300. Min Range: -3.5300
Max Act: 3.4360. Min Act: -0.1700
Data Index: 509268 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5300. Min Range: -3.5300
Max Act: 3.4360. Min Act: -0.1700
Data Index: 1483328 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5300. Min Range: -3.5300
Max Act: 3.4360. Min Act: -0.1700
Data Index: 4367654 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5300. Min Range: -3.5300
Max Act: 3.4360. Min Act: -0.1700
Data Index: 4703741 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19