Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 874 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.3139. Min Act: -0.1700
Data Index: 8688939 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.2826. Min Act: -0.1700
Data Index: 6854181 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.1576. Min Act: -0.1700
Data Index: 409423 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.1576. Min Act: -0.1700
Data Index: 397270 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.1264. Min Act: -0.1700
Data Index: 8412126 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.1264. Min Act: -0.1700
Data Index: 672697 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.1264. Min Act: -0.1700
Data Index: 7275522 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.1264. Min Act: -0.1700
Data Index: 3171844 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.0951. Min Act: -0.1700
Data Index: 4785967 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.0951. Min Act: -0.1700
Data Index: 6791124 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.0639. Min Act: -0.1700
Data Index: 2911915 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.0951. Min Act: -0.1700
Data Index: 1648029 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.0951. Min Act: -0.1700
Data Index: 6334604 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.0639. Min Act: -0.1700
Data Index: 6184460 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.0639. Min Act: -0.1700
Data Index: 5228847 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.0639. Min Act: -0.1700
Data Index: 5335369 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.0639. Min Act: -0.1700
Data Index: 426634 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.0326. Min Act: -0.1700
Data Index: 2710576 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.0326. Min Act: -0.1700
Data Index: 7102461 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.0014. Min Act: -0.1700
Data Index: 4351241 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19