Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4993 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.6466. Min Act: -0.1700
Data Index: 243773 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.6779. Min Act: -0.1700
Data Index: 1448996 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.6154. Min Act: -0.1700
Data Index: 3966074 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.6154. Min Act: -0.1700
Data Index: 8667087 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.6154. Min Act: -0.1700
Data Index: 1388182 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.5841. Min Act: -0.1700
Data Index: 7739786 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.6154. Min Act: -0.1700
Data Index: 4235912 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.5529. Min Act: -0.1700
Data Index: 3829036 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.5529. Min Act: -0.1700
Data Index: 724160 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.5529. Min Act: -0.1700
Data Index: 759186 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.5529. Min Act: -0.1700
Data Index: 871681 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.5216. Min Act: -0.1700
Data Index: 8526376 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.5216. Min Act: -0.1700
Data Index: 435745 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.4904. Min Act: -0.1700
Data Index: 5793132 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.4904. Min Act: -0.1700
Data Index: 1570901 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.4904. Min Act: -0.1700
Data Index: 6526473 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.4591. Min Act: -0.1700
Data Index: 6744822 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.4591. Min Act: -0.1700
Data Index: 6877497 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.4904. Min Act: -0.1700
Data Index: 1411837 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.4591. Min Act: -0.1700
Data Index: 7717388 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19