Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1151 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0779. Min Range: -4.0779
Max Act: 4.0779. Min Act: -0.1700
Data Index: 5065260 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0779. Min Range: -4.0779
Max Act: 4.0779. Min Act: -0.1700
Data Index: 7200616 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0779. Min Range: -4.0779
Max Act: 4.0779. Min Act: -0.1700
Data Index: 179537 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0779. Min Range: -4.0779
Max Act: 3.8903. Min Act: -0.1700
Data Index: 8400358 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0779. Min Range: -4.0779
Max Act: 3.8903. Min Act: -0.1700
Data Index: 1529700 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0779. Min Range: -4.0779
Max Act: 3.9216. Min Act: -0.1700
Data Index: 3620528 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0779. Min Range: -4.0779
Max Act: 3.8903. Min Act: -0.1700
Data Index: 8072168 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0779. Min Range: -4.0779
Max Act: 3.8591. Min Act: -0.1700
Data Index: 581730 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0779. Min Range: -4.0779
Max Act: 3.8591. Min Act: -0.1700
Data Index: 144595 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0779. Min Range: -4.0779
Max Act: 3.8591. Min Act: -0.1700
Data Index: 4024297 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0779. Min Range: -4.0779
Max Act: 3.8591. Min Act: -0.1700
Data Index: 3145774 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0779. Min Range: -4.0779
Max Act: 3.8591. Min Act: -0.1700
Data Index: 2343667 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0779. Min Range: -4.0779
Max Act: 3.8278. Min Act: -0.1700
Data Index: 121907 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0779. Min Range: -4.0779
Max Act: 3.8591. Min Act: -0.1700
Data Index: 5291909 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0779. Min Range: -4.0779
Max Act: 3.8278. Min Act: -0.1700
Data Index: 196256 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0779. Min Range: -4.0779
Max Act: 3.8278. Min Act: -0.1700
Data Index: 4990513 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0779. Min Range: -4.0779
Max Act: 3.8278. Min Act: -0.1700
Data Index: 6080052 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0779. Min Range: -4.0779
Max Act: 3.7965. Min Act: -0.1700
Data Index: 7425839 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0779. Min Range: -4.0779
Max Act: 3.7965. Min Act: -0.1700
Data Index: 5729032 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0779. Min Range: -4.0779
Max Act: 3.7965. Min Act: -0.1700
Data Index: 744330 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19