Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2248 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.1626. Min Act: -0.1700
Data Index: 1341102 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.1001. Min Act: -0.1700
Data Index: 1809508 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.1314. Min Act: -0.1700
Data Index: 1776592 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.1314. Min Act: -0.1700
Data Index: 4542453 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.1001. Min Act: -0.1700
Data Index: 8592002 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.1001. Min Act: -0.1700
Data Index: 8353769 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.0689. Min Act: -0.1700
Data Index: 5895448 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.0689. Min Act: -0.1700
Data Index: 737904 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.0689. Min Act: -0.1700
Data Index: 3781803 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.0376. Min Act: -0.1700
Data Index: 7358860 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.0376. Min Act: -0.1700
Data Index: 2310461 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.0064. Min Act: -0.1700
Data Index: 6905879 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.0064. Min Act: -0.1700
Data Index: 7479353 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1626. Min Range: -5.1626
Max Act: 4.9751. Min Act: -0.1700
Data Index: 401075 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.0064. Min Act: -0.1700
Data Index: 3818939 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.0376. Min Act: -0.1700
Data Index: 5568260 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1626. Min Range: -5.1626
Max Act: 4.9751. Min Act: -0.1700
Data Index: 3945885 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1626. Min Range: -5.1626
Max Act: 4.9751. Min Act: -0.1700
Data Index: 4245146 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1626. Min Range: -5.1626
Max Act: 4.9751. Min Act: -0.1700
Data Index: 7953819 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.0064. Min Act: -0.1700
Data Index: 7193189 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19