Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3386 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1576. Min Range: -5.1576
Max Act: 5.1576. Min Act: -0.1700
Data Index: 2656189 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1576. Min Range: -5.1576
Max Act: 4.8138. Min Act: -0.1700
Data Index: 6659596 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1576. Min Range: -5.1576
Max Act: 4.8138. Min Act: -0.1700
Data Index: 5350225 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1576. Min Range: -5.1576
Max Act: 4.7201. Min Act: -0.1700
Data Index: 6818156 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1576. Min Range: -5.1576
Max Act: 4.6888. Min Act: -0.1700
Data Index: 7241930 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1576. Min Range: -5.1576
Max Act: 4.5951. Min Act: -0.1700
Data Index: 7241927 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1576. Min Range: -5.1576
Max Act: 4.5638. Min Act: -0.1700
Data Index: 7199196 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1576. Min Range: -5.1576
Max Act: 4.5951. Min Act: -0.1700
Data Index: 3380315 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1576. Min Range: -5.1576
Max Act: 4.5951. Min Act: -0.1700
Data Index: 1132606 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1576. Min Range: -5.1576
Max Act: 4.5326. Min Act: -0.1700
Data Index: 3918016 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1576. Min Range: -5.1576
Max Act: 4.5013. Min Act: -0.1700
Data Index: 7752779 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1576. Min Range: -5.1576
Max Act: 4.4388. Min Act: -0.1700
Data Index: 8635079 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1576. Min Range: -5.1576
Max Act: 4.4388. Min Act: -0.1700
Data Index: 4770691 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1576. Min Range: -5.1576
Max Act: 4.4076. Min Act: -0.1700
Data Index: 1116562 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1576. Min Range: -5.1576
Max Act: 4.4388. Min Act: -0.1700
Data Index: 795048 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1576. Min Range: -5.1576
Max Act: 4.4076. Min Act: -0.1700
Data Index: 356669 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1576. Min Range: -5.1576
Max Act: 4.4076. Min Act: -0.1700
Data Index: 3425234 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1576. Min Range: -5.1576
Max Act: 4.4076. Min Act: -0.1700
Data Index: 6513574 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1576. Min Range: -5.1576
Max Act: 4.3763. Min Act: -0.1700
Data Index: 2773914 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1576. Min Range: -5.1576
Max Act: 4.4076. Min Act: -0.1700
Data Index: 7013369 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19