Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1290 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1238. Min Range: -6.1238
Max Act: 6.1238. Min Act: -0.1700
Data Index: 4487011 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1238. Min Range: -6.1238
Max Act: 6.0613. Min Act: -0.1700
Data Index: 3405128 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1238. Min Range: -6.1238
Max Act: 6.0301. Min Act: -0.1700
Data Index: 610028 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1238. Min Range: -6.1238
Max Act: 5.9676. Min Act: -0.1700
Data Index: 3428782 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1238. Min Range: -6.1238
Max Act: 5.9363. Min Act: -0.1700
Data Index: 8619784 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1238. Min Range: -6.1238
Max Act: 5.9051. Min Act: -0.1700
Data Index: 4936594 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1238. Min Range: -6.1238
Max Act: 5.9051. Min Act: -0.1700
Data Index: 258691 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1238. Min Range: -6.1238
Max Act: 5.8738. Min Act: -0.1700
Data Index: 1827737 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1238. Min Range: -6.1238
Max Act: 5.8426. Min Act: -0.1700
Data Index: 2387241 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1238. Min Range: -6.1238
Max Act: 5.8426. Min Act: -0.1700
Data Index: 8256348 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1238. Min Range: -6.1238
Max Act: 5.8113. Min Act: -0.1700
Data Index: 6390695 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1238. Min Range: -6.1238
Max Act: 5.8113. Min Act: -0.1700
Data Index: 4826529 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1238. Min Range: -6.1238
Max Act: 5.8113. Min Act: -0.1700
Data Index: 7641888 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1238. Min Range: -6.1238
Max Act: 5.8113. Min Act: -0.1700
Data Index: 2073447 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1238. Min Range: -6.1238
Max Act: 5.7488. Min Act: -0.1700
Data Index: 741719 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1238. Min Range: -6.1238
Max Act: 5.7488. Min Act: -0.1700
Data Index: 737895 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1238. Min Range: -6.1238
Max Act: 5.7488. Min Act: -0.1700
Data Index: 2995869 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1238. Min Range: -6.1238
Max Act: 5.7176. Min Act: -0.1700
Data Index: 6928449 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1238. Min Range: -6.1238
Max Act: 5.7176. Min Act: -0.1700
Data Index: 7747059 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1238. Min Range: -6.1238
Max Act: 5.7176. Min Act: -0.1700
Data Index: 484713 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19