Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4378 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7627. Min Range: -5.7627
Max Act: 5.7627. Min Act: -0.1700
Data Index: 1818939 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7627. Min Range: -5.7627
Max Act: 4.9502. Min Act: -0.1700
Data Index: 1601657 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7627. Min Range: -5.7627
Max Act: 4.9815. Min Act: -0.1700
Data Index: 6479201 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7627. Min Range: -5.7627
Max Act: 4.9190. Min Act: -0.1700
Data Index: 1547300 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7627. Min Range: -5.7627
Max Act: 4.8877. Min Act: -0.1700
Data Index: 4549930 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7627. Min Range: -5.7627
Max Act: 4.8877. Min Act: -0.1700
Data Index: 5860771 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7627. Min Range: -5.7627
Max Act: 4.8565. Min Act: -0.1700
Data Index: 627135 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7627. Min Range: -5.7627
Max Act: 4.8565. Min Act: -0.1700
Data Index: 3430812 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7627. Min Range: -5.7627
Max Act: 4.8565. Min Act: -0.1700
Data Index: 5158505 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7627. Min Range: -5.7627
Max Act: 4.7627. Min Act: -0.1700
Data Index: 4352655 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7627. Min Range: -5.7627
Max Act: 4.7315. Min Act: -0.1700
Data Index: 979581 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7627. Min Range: -5.7627
Max Act: 4.7627. Min Act: -0.1700
Data Index: 1954093 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7627. Min Range: -5.7627
Max Act: 4.7002. Min Act: -0.1700
Data Index: 4575065 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7627. Min Range: -5.7627
Max Act: 4.7002. Min Act: -0.1700
Data Index: 3102249 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7627. Min Range: -5.7627
Max Act: 4.6690. Min Act: -0.1700
Data Index: 8729474 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7627. Min Range: -5.7627
Max Act: 4.6690. Min Act: -0.1700
Data Index: 4909886 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7627. Min Range: -5.7627
Max Act: 4.6690. Min Act: -0.1700
Data Index: 6618643 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7627. Min Range: -5.7627
Max Act: 4.6065. Min Act: -0.1700
Data Index: 3447371 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7627. Min Range: -5.7627
Max Act: 4.6377. Min Act: -0.1700
Data Index: 7675072 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7627. Min Range: -5.7627
Max Act: 4.5752. Min Act: -0.1700
Data Index: 2078307 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19