Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 828 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0879. Min Range: -12.0879
Max Act: 12.0879. Min Act: -0.1700
Data Index: 3671082 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0879. Min Range: -12.0879
Max Act: 12.0879. Min Act: -0.1700
Data Index: 5132253 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0879. Min Range: -12.0879
Max Act: 11.9629. Min Act: -0.1700
Data Index: 924074 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0879. Min Range: -12.0879
Max Act: 11.9629. Min Act: -0.1700
Data Index: 4888539 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0879. Min Range: -12.0879
Max Act: 11.7754. Min Act: -0.1700
Data Index: 2034692 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0879. Min Range: -12.0879
Max Act: 11.7754. Min Act: -0.1700
Data Index: 8070551 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0879. Min Range: -12.0879
Max Act: 11.7129. Min Act: -0.1700
Data Index: 4093144 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0879. Min Range: -12.0879
Max Act: 11.6504. Min Act: -0.1700
Data Index: 729240 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0879. Min Range: -12.0879
Max Act: 11.6504. Min Act: -0.1700
Data Index: 6487031 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0879. Min Range: -12.0879
Max Act: 11.6504. Min Act: -0.1700
Data Index: 1588332 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0879. Min Range: -12.0879
Max Act: 11.6504. Min Act: -0.1700
Data Index: 4096187 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0879. Min Range: -12.0879
Max Act: 11.5879. Min Act: -0.1700
Data Index: 4151015 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0879. Min Range: -12.0879
Max Act: 11.6504. Min Act: -0.1700
Data Index: 232806 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0879. Min Range: -12.0879
Max Act: 11.5879. Min Act: -0.1700
Data Index: 2747197 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0879. Min Range: -12.0879
Max Act: 11.5879. Min Act: -0.1700
Data Index: 6100444 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0879. Min Range: -12.0879
Max Act: 11.5879. Min Act: -0.1700
Data Index: 8377222 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0879. Min Range: -12.0879
Max Act: 11.5254. Min Act: -0.1700
Data Index: 822974 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0879. Min Range: -12.0879
Max Act: 11.5254. Min Act: -0.1700
Data Index: 6596562 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0879. Min Range: -12.0879
Max Act: 11.5254. Min Act: -0.1700
Data Index: 1967833 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0879. Min Range: -12.0879
Max Act: 11.5254. Min Act: -0.1700
Data Index: 7184086 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19