Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 444 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9495. Min Range: -5.9495
Max Act: 5.9495. Min Act: -0.1700
Data Index: 4916271 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9495. Min Range: -5.9495
Max Act: 5.7932. Min Act: -0.1700
Data Index: 7541716 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9495. Min Range: -5.9495
Max Act: 5.7307. Min Act: -0.1700
Data Index: 3781381 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9495. Min Range: -5.9495
Max Act: 5.6682. Min Act: -0.1700
Data Index: 361852 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9495. Min Range: -5.9495
Max Act: 5.6370. Min Act: -0.1700
Data Index: 2515761 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9495. Min Range: -5.9495
Max Act: 5.6370. Min Act: -0.1700
Data Index: 4572034 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9495. Min Range: -5.9495
Max Act: 5.6057. Min Act: -0.1700
Data Index: 7723783 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9495. Min Range: -5.9495
Max Act: 5.5745. Min Act: -0.1700
Data Index: 2576989 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9495. Min Range: -5.9495
Max Act: 5.5745. Min Act: -0.1700
Data Index: 4200219 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9495. Min Range: -5.9495
Max Act: 5.5745. Min Act: -0.1700
Data Index: 402478 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9495. Min Range: -5.9495
Max Act: 5.5432. Min Act: -0.1700
Data Index: 861778 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9495. Min Range: -5.9495
Max Act: 5.5432. Min Act: -0.1700
Data Index: 5785350 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9495. Min Range: -5.9495
Max Act: 5.4807. Min Act: -0.1700
Data Index: 8410990 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9495. Min Range: -5.9495
Max Act: 5.5120. Min Act: -0.1700
Data Index: 3274852 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9495. Min Range: -5.9495
Max Act: 5.5120. Min Act: -0.1700
Data Index: 7197416 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9495. Min Range: -5.9495
Max Act: 5.5120. Min Act: -0.1700
Data Index: 2629752 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9495. Min Range: -5.9495
Max Act: 5.4807. Min Act: -0.1700
Data Index: 583483 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9495. Min Range: -5.9495
Max Act: 5.4807. Min Act: -0.1700
Data Index: 6788839 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9495. Min Range: -5.9495
Max Act: 5.5120. Min Act: -0.1700
Data Index: 2197370 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9495. Min Range: -5.9495
Max Act: 5.4495. Min Act: -0.1700
Data Index: 7857438 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19