Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6294 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1674. Min Range: -5.1674
Max Act: 5.1674. Min Act: -0.1700
Data Index: 845311 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.9174. Min Act: -0.1700
Data Index: 3146891 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.9174. Min Act: -0.1700
Data Index: 6290471 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.8861. Min Act: -0.1700
Data Index: 967632 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.8861. Min Act: -0.1700
Data Index: 5532815 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.8861. Min Act: -0.1700
Data Index: 5549966 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.8549. Min Act: -0.1700
Data Index: 3000780 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.8236. Min Act: -0.1700
Data Index: 8255595 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.7924. Min Act: -0.1700
Data Index: 3014573 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.7611. Min Act: -0.1700
Data Index: 5297323 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.7611. Min Act: -0.1700
Data Index: 432300 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.7611. Min Act: -0.1700
Data Index: 6367583 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.7611. Min Act: -0.1700
Data Index: 4324937 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.7611. Min Act: -0.1700
Data Index: 569484 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.7611. Min Act: -0.1700
Data Index: 992099 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.7299. Min Act: -0.1700
Data Index: 6058231 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.7299. Min Act: -0.1700
Data Index: 8197354 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.6986. Min Act: -0.1700
Data Index: 3772312 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.6986. Min Act: -0.1700
Data Index: 1916815 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.6674. Min Act: -0.1700
Data Index: 610842 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19