Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 757 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0242. Min Range: -9.0242
Max Act: 9.0242. Min Act: -0.1700
Data Index: 424966 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0242. Min Range: -9.0242
Max Act: 9.0242. Min Act: -0.1700
Data Index: 3423727 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0242. Min Range: -9.0242
Max Act: 8.8992. Min Act: -0.1700
Data Index: 1348993 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0242. Min Range: -9.0242
Max Act: 8.8367. Min Act: -0.1700
Data Index: 5270428 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0242. Min Range: -9.0242
Max Act: 8.8367. Min Act: -0.1700
Data Index: 193787 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0242. Min Range: -9.0242
Max Act: 8.7742. Min Act: -0.1700
Data Index: 673970 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0242. Min Range: -9.0242
Max Act: 8.7742. Min Act: -0.1700
Data Index: 5128584 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0242. Min Range: -9.0242
Max Act: 8.7117. Min Act: -0.1700
Data Index: 317949 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0242. Min Range: -9.0242
Max Act: 8.7117. Min Act: -0.1700
Data Index: 1163251 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0242. Min Range: -9.0242
Max Act: 8.6492. Min Act: -0.1700
Data Index: 4380885 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0242. Min Range: -9.0242
Max Act: 8.5867. Min Act: -0.1700
Data Index: 5269835 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0242. Min Range: -9.0242
Max Act: 8.5242. Min Act: -0.1700
Data Index: 103726 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0242. Min Range: -9.0242
Max Act: 8.5242. Min Act: -0.1700
Data Index: 1841169 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0242. Min Range: -9.0242
Max Act: 8.5242. Min Act: -0.1700
Data Index: 540517 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0242. Min Range: -9.0242
Max Act: 8.4617. Min Act: -0.1700
Data Index: 5446359 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0242. Min Range: -9.0242
Max Act: 8.4617. Min Act: -0.1700
Data Index: 3286023 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0242. Min Range: -9.0242
Max Act: 8.4617. Min Act: -0.1700
Data Index: 4605755 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0242. Min Range: -9.0242
Max Act: 8.3367. Min Act: -0.1700
Data Index: 747644 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0242. Min Range: -9.0242
Max Act: 8.3992. Min Act: -0.1700
Data Index: 3806875 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0242. Min Range: -9.0242
Max Act: 8.3992. Min Act: -0.1700
Data Index: 4259345 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19