Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2298 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2909. Min Range: -6.2909
Max Act: 6.2909. Min Act: -0.1700
Data Index: 8181744 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2909. Min Range: -6.2909
Max Act: 6.1034. Min Act: -0.1700
Data Index: 7866783 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2909. Min Range: -6.2909
Max Act: 6.0097. Min Act: -0.1700
Data Index: 2656763 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2909. Min Range: -6.2909
Max Act: 5.9159. Min Act: -0.1700
Data Index: 7468962 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2909. Min Range: -6.2909
Max Act: 5.9159. Min Act: -0.1700
Data Index: 1316676 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2909. Min Range: -6.2909
Max Act: 5.8847. Min Act: -0.1700
Data Index: 3372653 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2909. Min Range: -6.2909
Max Act: 5.8847. Min Act: -0.1700
Data Index: 1437033 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2909. Min Range: -6.2909
Max Act: 5.8534. Min Act: -0.1700
Data Index: 3000828 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2909. Min Range: -6.2909
Max Act: 5.8222. Min Act: -0.1700
Data Index: 5782159 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2909. Min Range: -6.2909
Max Act: 5.7909. Min Act: -0.1700
Data Index: 5054285 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2909. Min Range: -6.2909
Max Act: 5.7909. Min Act: -0.1700
Data Index: 623112 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2909. Min Range: -6.2909
Max Act: 5.8222. Min Act: -0.1700
Data Index: 4003509 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2909. Min Range: -6.2909
Max Act: 5.7284. Min Act: -0.1700
Data Index: 6748508 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2909. Min Range: -6.2909
Max Act: 5.7597. Min Act: -0.1700
Data Index: 6630506 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2909. Min Range: -6.2909
Max Act: 5.7284. Min Act: -0.1700
Data Index: 486902 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2909. Min Range: -6.2909
Max Act: 5.7284. Min Act: -0.1700
Data Index: 8091558 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2909. Min Range: -6.2909
Max Act: 5.7284. Min Act: -0.1700
Data Index: 6385377 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2909. Min Range: -6.2909
Max Act: 5.7284. Min Act: -0.1700
Data Index: 955940 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2909. Min Range: -6.2909
Max Act: 5.7284. Min Act: -0.1700
Data Index: 7268567 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2909. Min Range: -6.2909
Max Act: 5.7284. Min Act: -0.1700
Data Index: 3446908 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19