Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2535 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6567. Min Range: -7.6567
Max Act: 7.6567. Min Act: -0.1700
Data Index: 3457930 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6567. Min Range: -7.6567
Max Act: 7.3754. Min Act: -0.1700
Data Index: 6052514 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6567. Min Range: -7.6567
Max Act: 7.2504. Min Act: -0.1700
Data Index: 6913448 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6567. Min Range: -7.6567
Max Act: 7.1879. Min Act: -0.1700
Data Index: 7299773 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6567. Min Range: -7.6567
Max Act: 7.1567. Min Act: -0.1700
Data Index: 5922485 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6567. Min Range: -7.6567
Max Act: 6.9379. Min Act: -0.1700
Data Index: 7401824 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6567. Min Range: -7.6567
Max Act: 6.9067. Min Act: -0.1700
Data Index: 8289080 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6567. Min Range: -7.6567
Max Act: 6.8754. Min Act: -0.1700
Data Index: 5209224 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6567. Min Range: -7.6567
Max Act: 6.9067. Min Act: -0.1700
Data Index: 6085938 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6567. Min Range: -7.6567
Max Act: 6.8754. Min Act: -0.1700
Data Index: 5754062 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6567. Min Range: -7.6567
Max Act: 6.9067. Min Act: -0.1700
Data Index: 821116 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6567. Min Range: -7.6567
Max Act: 6.8754. Min Act: -0.1700
Data Index: 1422462 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6567. Min Range: -7.6567
Max Act: 6.8442. Min Act: -0.1700
Data Index: 2823436 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6567. Min Range: -7.6567
Max Act: 6.8129. Min Act: -0.1700
Data Index: 4600795 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6567. Min Range: -7.6567
Max Act: 6.7504. Min Act: -0.1700
Data Index: 3161509 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6567. Min Range: -7.6567
Max Act: 6.7817. Min Act: -0.1700
Data Index: 2946940 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6567. Min Range: -7.6567
Max Act: 6.7504. Min Act: -0.1700
Data Index: 5772261 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6567. Min Range: -7.6567
Max Act: 6.8129. Min Act: -0.1700
Data Index: 6875762 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6567. Min Range: -7.6567
Max Act: 6.7504. Min Act: -0.1700
Data Index: 4411687 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6567. Min Range: -7.6567
Max Act: 6.7817. Min Act: -0.1700
Data Index: 3179008 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19