Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1670 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8638. Min Range: -3.8638
Max Act: 3.8638. Min Act: -0.1700
Data Index: 3783615 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8638. Min Range: -3.8638
Max Act: 3.8169. Min Act: -0.1700
Data Index: 8729533 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8638. Min Range: -3.8638
Max Act: 3.7857. Min Act: -0.1700
Data Index: 7155060 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8638. Min Range: -3.8638
Max Act: 3.7700. Min Act: -0.1700
Data Index: 721395 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8638. Min Range: -3.8638
Max Act: 3.7700. Min Act: -0.1700
Data Index: 2840967 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8638. Min Range: -3.8638
Max Act: 3.7544. Min Act: -0.1700
Data Index: 8305796 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8638. Min Range: -3.8638
Max Act: 3.7231. Min Act: -0.1700
Data Index: 2379262 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8638. Min Range: -3.8638
Max Act: 3.7387. Min Act: -0.1700
Data Index: 8094055 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8638. Min Range: -3.8638
Max Act: 3.6918. Min Act: -0.1700
Data Index: 1587613 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8638. Min Range: -3.8638
Max Act: 3.6605. Min Act: -0.1700
Data Index: 4467660 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8638. Min Range: -3.8638
Max Act: 3.6762. Min Act: -0.1700
Data Index: 8020408 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8638. Min Range: -3.8638
Max Act: 3.6762. Min Act: -0.1700
Data Index: 1809065 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8638. Min Range: -3.8638
Max Act: 3.6605. Min Act: -0.1700
Data Index: 8488438 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8638. Min Range: -3.8638
Max Act: 3.6605. Min Act: -0.1700
Data Index: 4678353 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8638. Min Range: -3.8638
Max Act: 3.6605. Min Act: -0.1700
Data Index: 4267483 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8638. Min Range: -3.8638
Max Act: 3.6605. Min Act: -0.1700
Data Index: 7741650 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8638. Min Range: -3.8638
Max Act: 3.6449. Min Act: -0.1700
Data Index: 2215039 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8638. Min Range: -3.8638
Max Act: 3.6449. Min Act: -0.1700
Data Index: 7582526 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8638. Min Range: -3.8638
Max Act: 3.6449. Min Act: -0.1700
Data Index: 5340705 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8638. Min Range: -3.8638
Max Act: 3.6292. Min Act: -0.1700
Data Index: 3789822 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19