Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 108 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1651. Min Range: -9.1651
Max Act: 9.1651. Min Act: -0.1700
Data Index: 7409928 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1651. Min Range: -9.1651
Max Act: 8.2276. Min Act: -0.1700
Data Index: 8494842 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1651. Min Range: -9.1651
Max Act: 8.2276. Min Act: -0.1700
Data Index: 5566702 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1651. Min Range: -9.1651
Max Act: 8.2276. Min Act: -0.1700
Data Index: 8681103 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1651. Min Range: -9.1651
Max Act: 8.1651. Min Act: -0.1700
Data Index: 1708620 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1651. Min Range: -9.1651
Max Act: 8.1651. Min Act: -0.1700
Data Index: 376850 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1651. Min Range: -9.1651
Max Act: 8.1026. Min Act: -0.1700
Data Index: 5104313 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1651. Min Range: -9.1651
Max Act: 8.0714. Min Act: -0.1700
Data Index: 6087349 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1651. Min Range: -9.1651
Max Act: 8.0714. Min Act: -0.1700
Data Index: 3971483 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1651. Min Range: -9.1651
Max Act: 8.0401. Min Act: -0.1700
Data Index: 3799373 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1651. Min Range: -9.1651
Max Act: 8.0401. Min Act: -0.1700
Data Index: 392690 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1651. Min Range: -9.1651
Max Act: 8.0089. Min Act: -0.1700
Data Index: 3916711 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1651. Min Range: -9.1651
Max Act: 8.0089. Min Act: -0.1700
Data Index: 7943556 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1651. Min Range: -9.1651
Max Act: 7.9776. Min Act: -0.1700
Data Index: 5207447 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1651. Min Range: -9.1651
Max Act: 7.9776. Min Act: -0.1700
Data Index: 1616250 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1651. Min Range: -9.1651
Max Act: 7.9776. Min Act: -0.1700
Data Index: 7934434 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1651. Min Range: -9.1651
Max Act: 7.9776. Min Act: -0.1700
Data Index: 7849296 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1651. Min Range: -9.1651
Max Act: 7.9464. Min Act: -0.1700
Data Index: 7503393 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1651. Min Range: -9.1651
Max Act: 7.9464. Min Act: -0.1700
Data Index: 6249458 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1651. Min Range: -9.1651
Max Act: 7.9151. Min Act: -0.1700
Data Index: 4277968 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19