Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2760 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5929. Min Range: -7.5929
Max Act: 7.5929. Min Act: -0.1700
Data Index: 885429 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5929. Min Range: -7.5929
Max Act: 7.5616. Min Act: -0.1700
Data Index: 5616946 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5929. Min Range: -7.5929
Max Act: 7.5616. Min Act: -0.1700
Data Index: 3687747 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5929. Min Range: -7.5929
Max Act: 7.4366. Min Act: -0.1700
Data Index: 8522289 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5929. Min Range: -7.5929
Max Act: 7.4679. Min Act: -0.1700
Data Index: 3646657 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5929. Min Range: -7.5929
Max Act: 7.4366. Min Act: -0.1700
Data Index: 465732 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5929. Min Range: -7.5929
Max Act: 7.2179. Min Act: -0.1700
Data Index: 7136705 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5929. Min Range: -7.5929
Max Act: 7.1866. Min Act: -0.1700
Data Index: 370318 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5929. Min Range: -7.5929
Max Act: 7.1554. Min Act: -0.1700
Data Index: 8255205 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5929. Min Range: -7.5929
Max Act: 7.1554. Min Act: -0.1700
Data Index: 4562772 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5929. Min Range: -7.5929
Max Act: 7.1554. Min Act: -0.1700
Data Index: 3308184 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5929. Min Range: -7.5929
Max Act: 7.1554. Min Act: -0.1700
Data Index: 5693495 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5929. Min Range: -7.5929
Max Act: 7.0929. Min Act: -0.1700
Data Index: 5667728 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5929. Min Range: -7.5929
Max Act: 7.0616. Min Act: -0.1700
Data Index: 8669373 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5929. Min Range: -7.5929
Max Act: 6.9991. Min Act: -0.1700
Data Index: 5660125 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5929. Min Range: -7.5929
Max Act: 6.9991. Min Act: -0.1700
Data Index: 4182086 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5929. Min Range: -7.5929
Max Act: 6.9054. Min Act: -0.1700
Data Index: 1554776 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5929. Min Range: -7.5929
Max Act: 6.9054. Min Act: -0.1700
Data Index: 7459676 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5929. Min Range: -7.5929
Max Act: 6.8741. Min Act: -0.1700
Data Index: 3285020 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5929. Min Range: -7.5929
Max Act: 6.8429. Min Act: -0.1700
Data Index: 7846202 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19