Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2529 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4102. Min Range: -8.4102
Max Act: 8.4102. Min Act: -0.1700
Data Index: 7902395 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4102. Min Range: -8.4102
Max Act: 8.2227. Min Act: -0.1700
Data Index: 4975458 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4102. Min Range: -8.4102
Max Act: 8.1290. Min Act: -0.1700
Data Index: 4893767 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4102. Min Range: -8.4102
Max Act: 7.9102. Min Act: -0.1700
Data Index: 1590149 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4102. Min Range: -8.4102
Max Act: 7.8477. Min Act: -0.1700
Data Index: 5228770 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4102. Min Range: -8.4102
Max Act: 7.7852. Min Act: -0.1700
Data Index: 2125442 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4102. Min Range: -8.4102
Max Act: 7.7852. Min Act: -0.1700
Data Index: 8677238 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4102. Min Range: -8.4102
Max Act: 7.5977. Min Act: -0.1700
Data Index: 7526183 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4102. Min Range: -8.4102
Max Act: 7.5665. Min Act: -0.1700
Data Index: 7868415 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4102. Min Range: -8.4102
Max Act: 7.5352. Min Act: -0.1700
Data Index: 3501532 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4102. Min Range: -8.4102
Max Act: 7.5040. Min Act: -0.1700
Data Index: 2378990 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4102. Min Range: -8.4102
Max Act: 7.4727. Min Act: -0.1700
Data Index: 2498128 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4102. Min Range: -8.4102
Max Act: 7.4727. Min Act: -0.1700
Data Index: 2145969 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4102. Min Range: -8.4102
Max Act: 7.4415. Min Act: -0.1700
Data Index: 4380023 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4102. Min Range: -8.4102
Max Act: 7.4727. Min Act: -0.1700
Data Index: 8451485 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4102. Min Range: -8.4102
Max Act: 7.4102. Min Act: -0.1700
Data Index: 1961807 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4102. Min Range: -8.4102
Max Act: 7.3790. Min Act: -0.1700
Data Index: 19886 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4102. Min Range: -8.4102
Max Act: 7.3165. Min Act: -0.1700
Data Index: 4426406 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4102. Min Range: -8.4102
Max Act: 7.3165. Min Act: -0.1700
Data Index: 8345832 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4102. Min Range: -8.4102
Max Act: 7.2852. Min Act: -0.1700
Data Index: 8716777 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19