Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4353. Min Range: -4.4353
Max Act: 4.4353. Min Act: -0.1699
Data Index: 5300017 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4353. Min Range: -4.4353
Max Act: 4.4353. Min Act: -0.1699
Data Index: 8431728 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4353. Min Range: -4.4353
Max Act: 4.3728. Min Act: -0.1700
Data Index: 6744051 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4353. Min Range: -4.4353
Max Act: 4.3728. Min Act: -0.1700
Data Index: 2776735 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4353. Min Range: -4.4353
Max Act: 4.3103. Min Act: -0.1700
Data Index: 634353 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4353. Min Range: -4.4353
Max Act: 4.3415. Min Act: -0.1700
Data Index: 8655831 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4353. Min Range: -4.4353
Max Act: 4.3103. Min Act: -0.1700
Data Index: 2643704 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4353. Min Range: -4.4353
Max Act: 4.3103. Min Act: -0.1700
Data Index: 8229819 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4353. Min Range: -4.4353
Max Act: 4.3103. Min Act: -0.1700
Data Index: 2045505 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4353. Min Range: -4.4353
Max Act: 4.2790. Min Act: -0.1700
Data Index: 7364432 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4353. Min Range: -4.4353
Max Act: 4.2790. Min Act: -0.1700
Data Index: 3852579 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4353. Min Range: -4.4353
Max Act: 4.3103. Min Act: -0.1700
Data Index: 323908 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4353. Min Range: -4.4353
Max Act: 4.2790. Min Act: -0.1700
Data Index: 2191016 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4353. Min Range: -4.4353
Max Act: 4.2790. Min Act: -0.1700
Data Index: 8601772 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4353. Min Range: -4.4353
Max Act: 4.2790. Min Act: -0.1700
Data Index: 3542005 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4353. Min Range: -4.4353
Max Act: 4.2790. Min Act: -0.1700
Data Index: 3983351 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4353. Min Range: -4.4353
Max Act: 4.2790. Min Act: -0.1700
Data Index: 1846254 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4353. Min Range: -4.4353
Max Act: 4.2478. Min Act: -0.1700
Data Index: 5238204 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4353. Min Range: -4.4353
Max Act: 4.2790. Min Act: -0.1700
Data Index: 2750010 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4353. Min Range: -4.4353
Max Act: 4.2790. Min Act: -0.1700
Data Index: 8746802 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19