Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5234 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6543. Min Range: -7.6543
Max Act: 7.6543. Min Act: -0.1700
Data Index: 7526316 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6543. Min Range: -7.6543
Max Act: 7.2793. Min Act: -0.1700
Data Index: 8826377 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6543. Min Range: -7.6543
Max Act: 7.1855. Min Act: -0.1700
Data Index: 6599595 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6543. Min Range: -7.6543
Max Act: 7.1855. Min Act: -0.1700
Data Index: 6315101 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6543. Min Range: -7.6543
Max Act: 7.1543. Min Act: -0.1700
Data Index: 4570853 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6543. Min Range: -7.6543
Max Act: 7.1230. Min Act: -0.1700
Data Index: 8819581 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6543. Min Range: -7.6543
Max Act: 7.0918. Min Act: -0.1700
Data Index: 8482718 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6543. Min Range: -7.6543
Max Act: 7.0918. Min Act: -0.1700
Data Index: 8284422 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6543. Min Range: -7.6543
Max Act: 7.0605. Min Act: -0.1700
Data Index: 3426016 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6543. Min Range: -7.6543
Max Act: 7.0605. Min Act: -0.1700
Data Index: 5805938 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6543. Min Range: -7.6543
Max Act: 6.9980. Min Act: -0.1700
Data Index: 4281909 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6543. Min Range: -7.6543
Max Act: 6.9980. Min Act: -0.1700
Data Index: 8784409 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6543. Min Range: -7.6543
Max Act: 6.9668. Min Act: -0.1700
Data Index: 4821238 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6543. Min Range: -7.6543
Max Act: 6.9355. Min Act: -0.1700
Data Index: 2502687 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6543. Min Range: -7.6543
Max Act: 6.9355. Min Act: -0.1700
Data Index: 364192 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6543. Min Range: -7.6543
Max Act: 6.8730. Min Act: -0.1700
Data Index: 3458976 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6543. Min Range: -7.6543
Max Act: 6.8730. Min Act: -0.1700
Data Index: 7966888 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6543. Min Range: -7.6543
Max Act: 6.8418. Min Act: -0.1700
Data Index: 4126866 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6543. Min Range: -7.6543
Max Act: 6.8418. Min Act: -0.1700
Data Index: 3221493 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6543. Min Range: -7.6543
Max Act: 6.8418. Min Act: -0.1700
Data Index: 7105605 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19