Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 450 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2234. Min Range: -8.2234
Max Act: 8.2234. Min Act: -0.1700
Data Index: 1792766 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2234. Min Range: -8.2234
Max Act: 7.9734. Min Act: -0.1700
Data Index: 8044752 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2234. Min Range: -8.2234
Max Act: 7.8484. Min Act: -0.1700
Data Index: 7351034 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2234. Min Range: -8.2234
Max Act: 7.9109. Min Act: -0.1700
Data Index: 2627486 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2234. Min Range: -8.2234
Max Act: 7.8484. Min Act: -0.1700
Data Index: 8042063 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2234. Min Range: -8.2234
Max Act: 7.8484. Min Act: -0.1700
Data Index: 4314444 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2234. Min Range: -8.2234
Max Act: 7.7859. Min Act: -0.1700
Data Index: 266891 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2234. Min Range: -8.2234
Max Act: 7.7859. Min Act: -0.1700
Data Index: 5412219 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2234. Min Range: -8.2234
Max Act: 7.7859. Min Act: -0.1700
Data Index: 3654579 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2234. Min Range: -8.2234
Max Act: 7.7859. Min Act: -0.1700
Data Index: 6836047 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2234. Min Range: -8.2234
Max Act: 7.6609. Min Act: -0.1700
Data Index: 2673429 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2234. Min Range: -8.2234
Max Act: 7.7234. Min Act: -0.1700
Data Index: 7520708 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2234. Min Range: -8.2234
Max Act: 7.7234. Min Act: -0.1700
Data Index: 8008050 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2234. Min Range: -8.2234
Max Act: 7.7234. Min Act: -0.1700
Data Index: 1481415 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2234. Min Range: -8.2234
Max Act: 7.7234. Min Act: -0.1700
Data Index: 3812494 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2234. Min Range: -8.2234
Max Act: 7.6609. Min Act: -0.1700
Data Index: 7993382 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2234. Min Range: -8.2234
Max Act: 7.5984. Min Act: -0.1700
Data Index: 1635209 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2234. Min Range: -8.2234
Max Act: 7.6609. Min Act: -0.1700
Data Index: 545452 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2234. Min Range: -8.2234
Max Act: 7.6609. Min Act: -0.1700
Data Index: 3156556 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2234. Min Range: -8.2234
Max Act: 7.6609. Min Act: -0.1700
Data Index: 679318 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19