Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3787 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2637. Min Range: -5.2637
Max Act: 5.2637. Min Act: -0.1700
Data Index: 508054 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2637. Min Range: -5.2637
Max Act: 5.1387. Min Act: -0.1700
Data Index: 913491 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2637. Min Range: -5.2637
Max Act: 5.0137. Min Act: -0.1700
Data Index: 3811296 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2637. Min Range: -5.2637
Max Act: 4.9825. Min Act: -0.1700
Data Index: 6314774 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2637. Min Range: -5.2637
Max Act: 4.9825. Min Act: -0.1700
Data Index: 8073410 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2637. Min Range: -5.2637
Max Act: 4.9825. Min Act: -0.1700
Data Index: 414202 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2637. Min Range: -5.2637
Max Act: 4.9512. Min Act: -0.1700
Data Index: 4740557 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2637. Min Range: -5.2637
Max Act: 4.9200. Min Act: -0.1700
Data Index: 4701352 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2637. Min Range: -5.2637
Max Act: 4.9200. Min Act: -0.1700
Data Index: 7808903 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2637. Min Range: -5.2637
Max Act: 4.9200. Min Act: -0.1700
Data Index: 2790556 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2637. Min Range: -5.2637
Max Act: 4.9512. Min Act: -0.1700
Data Index: 4934574 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2637. Min Range: -5.2637
Max Act: 4.8575. Min Act: -0.1700
Data Index: 1228103 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2637. Min Range: -5.2637
Max Act: 4.8575. Min Act: -0.1700
Data Index: 2406983 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2637. Min Range: -5.2637
Max Act: 4.8575. Min Act: -0.1700
Data Index: 6465875 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2637. Min Range: -5.2637
Max Act: 4.8262. Min Act: -0.1700
Data Index: 5108676 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2637. Min Range: -5.2637
Max Act: 4.8262. Min Act: -0.1700
Data Index: 3742833 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2637. Min Range: -5.2637
Max Act: 4.7637. Min Act: -0.1700
Data Index: 7270125 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2637. Min Range: -5.2637
Max Act: 4.7950. Min Act: -0.1700
Data Index: 1915539 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2637. Min Range: -5.2637
Max Act: 4.7637. Min Act: -0.1700
Data Index: 6029825 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2637. Min Range: -5.2637
Max Act: 4.7637. Min Act: -0.1700
Data Index: 2125542 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19