Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3516 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9752. Min Range: -7.9752
Max Act: 7.9752. Min Act: -0.1700
Data Index: 7337702 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9752. Min Range: -7.9752
Max Act: 7.9127. Min Act: -0.1700
Data Index: 1176182 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9752. Min Range: -7.9752
Max Act: 7.9127. Min Act: -0.1700
Data Index: 7414250 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9752. Min Range: -7.9752
Max Act: 7.9127. Min Act: -0.1700
Data Index: 4177167 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9752. Min Range: -7.9752
Max Act: 7.9127. Min Act: -0.1700
Data Index: 2260837 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9752. Min Range: -7.9752
Max Act: 7.8502. Min Act: -0.1700
Data Index: 7878717 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9752. Min Range: -7.9752
Max Act: 7.7252. Min Act: -0.1700
Data Index: 1957609 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9752. Min Range: -7.9752
Max Act: 7.7252. Min Act: -0.1700
Data Index: 4754164 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9752. Min Range: -7.9752
Max Act: 7.7252. Min Act: -0.1700
Data Index: 5759440 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9752. Min Range: -7.9752
Max Act: 7.6002. Min Act: -0.1700
Data Index: 1412445 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9752. Min Range: -7.9752
Max Act: 7.6002. Min Act: -0.1700
Data Index: 2268494 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9752. Min Range: -7.9752
Max Act: 7.4752. Min Act: -0.1700
Data Index: 2583271 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9752. Min Range: -7.9752
Max Act: 7.5377. Min Act: -0.1700
Data Index: 7361156 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9752. Min Range: -7.9752
Max Act: 7.5377. Min Act: -0.1700
Data Index: 6896378 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9752. Min Range: -7.9752
Max Act: 7.5377. Min Act: -0.1700
Data Index: 615858 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9752. Min Range: -7.9752
Max Act: 7.5377. Min Act: -0.1700
Data Index: 533108 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9752. Min Range: -7.9752
Max Act: 7.5377. Min Act: -0.1700
Data Index: 6020246 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9752. Min Range: -7.9752
Max Act: 7.5377. Min Act: -0.1700
Data Index: 2262896 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9752. Min Range: -7.9752
Max Act: 7.5377. Min Act: -0.1700
Data Index: 8183496 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9752. Min Range: -7.9752
Max Act: 7.5377. Min Act: -0.1700
Data Index: 1380885 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19