Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3203 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9018. Min Range: -3.9018
Max Act: 3.9018. Min Act: -0.1700
Data Index: 6088971 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9018. Min Range: -3.9018
Max Act: 3.8705. Min Act: -0.1700
Data Index: 7314517 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9018. Min Range: -3.9018
Max Act: 3.7454. Min Act: -0.1700
Data Index: 7471003 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9018. Min Range: -3.9018
Max Act: 3.7611. Min Act: -0.1700
Data Index: 1410605 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9018. Min Range: -3.9018
Max Act: 3.7298. Min Act: -0.1700
Data Index: 186575 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9018. Min Range: -3.9018
Max Act: 3.6516. Min Act: -0.1700
Data Index: 1550347 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9018. Min Range: -3.9018
Max Act: 3.6359. Min Act: -0.1700
Data Index: 3594988 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9018. Min Range: -3.9018
Max Act: 3.6359. Min Act: -0.1700
Data Index: 5670855 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9018. Min Range: -3.9018
Max Act: 3.6046. Min Act: -0.1700
Data Index: 7153160 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9018. Min Range: -3.9018
Max Act: 3.6046. Min Act: -0.1700
Data Index: 6353369 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9018. Min Range: -3.9018
Max Act: 3.6046. Min Act: -0.1700
Data Index: 1196229 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9018. Min Range: -3.9018
Max Act: 3.5577. Min Act: -0.1700
Data Index: 2218769 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9018. Min Range: -3.9018
Max Act: 3.5733. Min Act: -0.1700
Data Index: 8124324 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9018. Min Range: -3.9018
Max Act: 3.5577. Min Act: -0.1700
Data Index: 3913102 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9018. Min Range: -3.9018
Max Act: 3.5420. Min Act: -0.1700
Data Index: 8659677 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9018. Min Range: -3.9018
Max Act: 3.5420. Min Act: -0.1700
Data Index: 6196505 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9018. Min Range: -3.9018
Max Act: 3.5420. Min Act: -0.1700
Data Index: 2120888 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9018. Min Range: -3.9018
Max Act: 3.5420. Min Act: -0.1700
Data Index: 7113718 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9018. Min Range: -3.9018
Max Act: 3.5420. Min Act: -0.1700
Data Index: 1032655 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9018. Min Range: -3.9018
Max Act: 3.5107. Min Act: -0.1700
Data Index: 7785636 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19