Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4651 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8674. Min Range: -5.8674
Max Act: 5.8674. Min Act: -0.1700
Data Index: 4749507 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8674. Min Range: -5.8674
Max Act: 5.7424. Min Act: -0.1700
Data Index: 2954912 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8674. Min Range: -5.8674
Max Act: 5.7424. Min Act: -0.1700
Data Index: 3204651 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8674. Min Range: -5.8674
Max Act: 5.5861. Min Act: -0.1700
Data Index: 3654413 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8674. Min Range: -5.8674
Max Act: 5.5236. Min Act: -0.1700
Data Index: 2777352 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8674. Min Range: -5.8674
Max Act: 5.4924. Min Act: -0.1700
Data Index: 252927 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8674. Min Range: -5.8674
Max Act: 5.4924. Min Act: -0.1700
Data Index: 8318384 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8674. Min Range: -5.8674
Max Act: 5.4924. Min Act: -0.1700
Data Index: 5968544 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8674. Min Range: -5.8674
Max Act: 5.4611. Min Act: -0.1700
Data Index: 7369349 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8674. Min Range: -5.8674
Max Act: 5.4924. Min Act: -0.1700
Data Index: 961444 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8674. Min Range: -5.8674
Max Act: 5.4611. Min Act: -0.1700
Data Index: 8108102 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8674. Min Range: -5.8674
Max Act: 5.4611. Min Act: -0.1700
Data Index: 5144322 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8674. Min Range: -5.8674
Max Act: 5.4299. Min Act: -0.1700
Data Index: 3066094 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8674. Min Range: -5.8674
Max Act: 5.4299. Min Act: -0.1700
Data Index: 4161310 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8674. Min Range: -5.8674
Max Act: 5.4299. Min Act: -0.1700
Data Index: 753562 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8674. Min Range: -5.8674
Max Act: 5.3986. Min Act: -0.1700
Data Index: 5846287 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8674. Min Range: -5.8674
Max Act: 5.4299. Min Act: -0.1700
Data Index: 4593209 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8674. Min Range: -5.8674
Max Act: 5.3986. Min Act: -0.1700
Data Index: 7581699 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8674. Min Range: -5.8674
Max Act: 5.3986. Min Act: -0.1700
Data Index: 6695535 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8674. Min Range: -5.8674
Max Act: 5.3986. Min Act: -0.1700
Data Index: 1190183 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19