Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3112 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.3482. Min Act: -0.1700
Data Index: 2139440 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.3169. Min Act: -0.1700
Data Index: 4298277 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.2544. Min Act: -0.1700
Data Index: 1694393 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.2544. Min Act: -0.1700
Data Index: 5230763 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.2857. Min Act: -0.1700
Data Index: 6423086 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.2232. Min Act: -0.1700
Data Index: 3789426 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.2544. Min Act: -0.1700
Data Index: 2008513 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.1919. Min Act: -0.1700
Data Index: 5530941 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.2232. Min Act: -0.1700
Data Index: 8306740 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.2232. Min Act: -0.1700
Data Index: 4707173 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.2232. Min Act: -0.1700
Data Index: 2544743 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.2232. Min Act: -0.1700
Data Index: 5499107 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.2232. Min Act: -0.1700
Data Index: 3862844 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.2232. Min Act: -0.1700
Data Index: 6626030 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.1919. Min Act: -0.1700
Data Index: 3340660 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.2232. Min Act: -0.1700
Data Index: 4941005 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.1294. Min Act: -0.1700
Data Index: 8407608 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.1607. Min Act: -0.1700
Data Index: 7418935 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.1607. Min Act: -0.1700
Data Index: 3979697 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.1607. Min Act: -0.1700
Data Index: 1600722 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19