Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2052 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.9920. Min Act: -0.1700
Data Index: 3480577 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.9295. Min Act: -0.1700
Data Index: 5910912 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.9295. Min Act: -0.1700
Data Index: 5996220 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.8982. Min Act: -0.1700
Data Index: 823681 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.8982. Min Act: -0.1700
Data Index: 5996219 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.8670. Min Act: -0.1700
Data Index: 5644234 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.8045. Min Act: -0.1700
Data Index: 8715101 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.8045. Min Act: -0.1700
Data Index: 5925194 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.7420. Min Act: -0.1700
Data Index: 8278531 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.7732. Min Act: -0.1700
Data Index: 7441574 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.7732. Min Act: -0.1700
Data Index: 7441575 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.7107. Min Act: -0.1700
Data Index: 5996223 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.7420. Min Act: -0.1700
Data Index: 476607 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.7420. Min Act: -0.1700
Data Index: 3172737 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.7420. Min Act: -0.1700
Data Index: 8239337 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.7107. Min Act: -0.1700
Data Index: 1476123 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.7420. Min Act: -0.1700
Data Index: 230768 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.7107. Min Act: -0.1700
Data Index: 5357102 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.7107. Min Act: -0.1700
Data Index: 2055289 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.6795. Min Act: -0.1700
Data Index: 4908012 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19