Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3276 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4779. Min Range: -8.4779
Max Act: 8.4779. Min Act: -0.1700
Data Index: 2051016 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4779. Min Range: -8.4779
Max Act: 8.2279. Min Act: -0.1700
Data Index: 3230201 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4779. Min Range: -8.4779
Max Act: 8.2279. Min Act: -0.1700
Data Index: 2460665 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4779. Min Range: -8.4779
Max Act: 8.1654. Min Act: -0.1700
Data Index: 5600237 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4779. Min Range: -8.4779
Max Act: 8.1029. Min Act: -0.1700
Data Index: 7855613 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4779. Min Range: -8.4779
Max Act: 8.0404. Min Act: -0.1700
Data Index: 4872405 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4779. Min Range: -8.4779
Max Act: 7.9779. Min Act: -0.1700
Data Index: 424533 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4779. Min Range: -8.4779
Max Act: 7.9779. Min Act: -0.1700
Data Index: 4853176 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4779. Min Range: -8.4779
Max Act: 7.9154. Min Act: -0.1700
Data Index: 585189 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4779. Min Range: -8.4779
Max Act: 7.7904. Min Act: -0.1700
Data Index: 1898949 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4779. Min Range: -8.4779
Max Act: 7.8529. Min Act: -0.1700
Data Index: 4398141 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4779. Min Range: -8.4779
Max Act: 7.9154. Min Act: -0.1699
Data Index: 3888679 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4779. Min Range: -8.4779
Max Act: 7.8529. Min Act: -0.1700
Data Index: 3209336 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4779. Min Range: -8.4779
Max Act: 7.7904. Min Act: -0.1700
Data Index: 2424622 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4779. Min Range: -8.4779
Max Act: 7.7904. Min Act: -0.1700
Data Index: 6704322 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4779. Min Range: -8.4779
Max Act: 7.7904. Min Act: -0.1700
Data Index: 819832 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4779. Min Range: -8.4779
Max Act: 7.7904. Min Act: -0.1700
Data Index: 2391799 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4779. Min Range: -8.4779
Max Act: 7.7904. Min Act: -0.1700
Data Index: 5064317 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4779. Min Range: -8.4779
Max Act: 7.7904. Min Act: -0.1700
Data Index: 7518846 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4779. Min Range: -8.4779
Max Act: 7.7904. Min Act: -0.1700
Data Index: 4621648 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19