Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3630 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4327. Min Range: -5.4327
Max Act: 5.4014. Min Act: -0.1700
Data Index: 6148938 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4327. Min Range: -5.4327
Max Act: 5.4014. Min Act: -0.1700
Data Index: 6054562 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4327. Min Range: -5.4327
Max Act: 5.4327. Min Act: -0.1700
Data Index: 5012984 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4327. Min Range: -5.4327
Max Act: 5.4014. Min Act: -0.1700
Data Index: 3156873 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4327. Min Range: -5.4327
Max Act: 5.4014. Min Act: -0.1700
Data Index: 6143240 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4327. Min Range: -5.4327
Max Act: 5.3702. Min Act: -0.1700
Data Index: 7024386 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4327. Min Range: -5.4327
Max Act: 5.3389. Min Act: -0.1700
Data Index: 8433559 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4327. Min Range: -5.4327
Max Act: 5.3389. Min Act: -0.1700
Data Index: 1895448 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4327. Min Range: -5.4327
Max Act: 5.3389. Min Act: -0.1700
Data Index: 4091866 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4327. Min Range: -5.4327
Max Act: 5.2764. Min Act: -0.1700
Data Index: 4511136 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4327. Min Range: -5.4327
Max Act: 5.2452. Min Act: -0.1700
Data Index: 3261816 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4327. Min Range: -5.4327
Max Act: 5.2452. Min Act: -0.1700
Data Index: 2080098 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4327. Min Range: -5.4327
Max Act: 5.2139. Min Act: -0.1700
Data Index: 6691278 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4327. Min Range: -5.4327
Max Act: 5.2139. Min Act: -0.1700
Data Index: 1921536 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4327. Min Range: -5.4327
Max Act: 5.2139. Min Act: -0.1700
Data Index: 866403 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4327. Min Range: -5.4327
Max Act: 5.2139. Min Act: -0.1700
Data Index: 850248 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4327. Min Range: -5.4327
Max Act: 5.2139. Min Act: -0.1700
Data Index: 7777867 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4327. Min Range: -5.4327
Max Act: 5.1827. Min Act: -0.1700
Data Index: 4013893 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4327. Min Range: -5.4327
Max Act: 5.1827. Min Act: -0.1700
Data Index: 2136760 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4327. Min Range: -5.4327
Max Act: 5.1514. Min Act: -0.1700
Data Index: 7682570 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19