Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 332 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5338. Min Range: -7.5338
Max Act: 7.5338. Min Act: -0.1700
Data Index: 6969796 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5338. Min Range: -7.5338
Max Act: 7.2838. Min Act: -0.1700
Data Index: 1669258 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5338. Min Range: -7.5338
Max Act: 7.1588. Min Act: -0.1700
Data Index: 7332743 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5338. Min Range: -7.5338
Max Act: 7.1588. Min Act: -0.1700
Data Index: 8229844 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5338. Min Range: -7.5338
Max Act: 7.1588. Min Act: -0.1700
Data Index: 2866935 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5338. Min Range: -7.5338
Max Act: 7.1588. Min Act: -0.1700
Data Index: 2098191 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5338. Min Range: -7.5338
Max Act: 7.0963. Min Act: -0.1700
Data Index: 1050912 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5338. Min Range: -7.5338
Max Act: 7.0963. Min Act: -0.1700
Data Index: 7164339 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5338. Min Range: -7.5338
Max Act: 7.0338. Min Act: -0.1700
Data Index: 4873089 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5338. Min Range: -7.5338
Max Act: 7.0338. Min Act: -0.1700
Data Index: 600707 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5338. Min Range: -7.5338
Max Act: 7.0338. Min Act: -0.1700
Data Index: 7151846 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5338. Min Range: -7.5338
Max Act: 7.0338. Min Act: -0.1700
Data Index: 4028927 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5338. Min Range: -7.5338
Max Act: 7.0026. Min Act: -0.1700
Data Index: 1735800 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5338. Min Range: -7.5338
Max Act: 7.0026. Min Act: -0.1700
Data Index: 105915 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5338. Min Range: -7.5338
Max Act: 6.9713. Min Act: -0.1700
Data Index: 1518582 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5338. Min Range: -7.5338
Max Act: 6.9713. Min Act: -0.1700
Data Index: 2647249 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5338. Min Range: -7.5338
Max Act: 6.9401. Min Act: -0.1700
Data Index: 6762935 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5338. Min Range: -7.5338
Max Act: 6.9713. Min Act: -0.1700
Data Index: 6156847 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5338. Min Range: -7.5338
Max Act: 6.9401. Min Act: -0.1700
Data Index: 1401453 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5338. Min Range: -7.5338
Max Act: 6.9713. Min Act: -0.1700
Data Index: 230291 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19