Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 495 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3434. Min Range: -5.3434
Max Act: 5.3434. Min Act: -0.1700
Data Index: 1486553 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3434. Min Range: -5.3434
Max Act: 5.2809. Min Act: -0.1700
Data Index: 243870 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3434. Min Range: -5.3434
Max Act: 5.1871. Min Act: -0.1700
Data Index: 7169419 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3434. Min Range: -5.3434
Max Act: 5.1559. Min Act: -0.1700
Data Index: 6292586 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3434. Min Range: -5.3434
Max Act: 5.1871. Min Act: -0.1700
Data Index: 3849522 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3434. Min Range: -5.3434
Max Act: 5.1246. Min Act: -0.1700
Data Index: 3243070 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3434. Min Range: -5.3434
Max Act: 5.1246. Min Act: -0.1700
Data Index: 678445 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3434. Min Range: -5.3434
Max Act: 5.0934. Min Act: -0.1700
Data Index: 3032601 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3434. Min Range: -5.3434
Max Act: 5.0934. Min Act: -0.1700
Data Index: 8075692 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3434. Min Range: -5.3434
Max Act: 5.0621. Min Act: -0.1700
Data Index: 6771273 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3434. Min Range: -5.3434
Max Act: 5.0621. Min Act: -0.1700
Data Index: 8691168 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3434. Min Range: -5.3434
Max Act: 5.0621. Min Act: -0.1700
Data Index: 728873 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3434. Min Range: -5.3434
Max Act: 5.0309. Min Act: -0.1700
Data Index: 4618803 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3434. Min Range: -5.3434
Max Act: 5.0309. Min Act: -0.1700
Data Index: 1591084 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3434. Min Range: -5.3434
Max Act: 5.0309. Min Act: -0.1700
Data Index: 5597295 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3434. Min Range: -5.3434
Max Act: 4.9996. Min Act: -0.1700
Data Index: 1834035 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3434. Min Range: -5.3434
Max Act: 5.0309. Min Act: -0.1700
Data Index: 8448793 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3434. Min Range: -5.3434
Max Act: 5.0309. Min Act: -0.1700
Data Index: 862969 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3434. Min Range: -5.3434
Max Act: 4.9996. Min Act: -0.1700
Data Index: 5659331 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3434. Min Range: -5.3434
Max Act: 4.9996. Min Act: -0.1700
Data Index: 990005 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19