Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 853 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.9504. Min Act: -0.1700
Data Index: 6037368 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.7004. Min Act: -0.1700
Data Index: 5254192 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.7316. Min Act: -0.1700
Data Index: 1986364 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.7004. Min Act: -0.1700
Data Index: 7016736 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.6379. Min Act: -0.1700
Data Index: 7710114 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.5754. Min Act: -0.1700
Data Index: 6532179 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.5129. Min Act: -0.1700
Data Index: 5697139 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.5129. Min Act: -0.1700
Data Index: 6523026 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.5129. Min Act: -0.1700
Data Index: 1254046 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.4816. Min Act: -0.1700
Data Index: 4561827 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.4191. Min Act: -0.1700
Data Index: 608946 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.4504. Min Act: -0.1700
Data Index: 4441131 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.4504. Min Act: -0.1700
Data Index: 6847906 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.4504. Min Act: -0.1700
Data Index: 5449379 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.4191. Min Act: -0.1700
Data Index: 2359382 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.4191. Min Act: -0.1700
Data Index: 2142599 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.4191. Min Act: -0.1700
Data Index: 3454841 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.3879. Min Act: -0.1700
Data Index: 5099989 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.3879. Min Act: -0.1700
Data Index: 3222891 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.3879. Min Act: -0.1700
Data Index: 5804899 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19