Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5277 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2764. Min Range: -9.2764
Max Act: 9.2764. Min Act: -0.1700
Data Index: 3600476 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2764. Min Range: -9.2764
Max Act: 8.5264. Min Act: -0.1700
Data Index: 5047537 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2764. Min Range: -9.2764
Max Act: 8.4014. Min Act: -0.1700
Data Index: 1876126 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2764. Min Range: -9.2764
Max Act: 8.4639. Min Act: -0.1700
Data Index: 1806236 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2764. Min Range: -9.2764
Max Act: 8.4639. Min Act: -0.1700
Data Index: 5843676 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2764. Min Range: -9.2764
Max Act: 8.4639. Min Act: -0.1700
Data Index: 4692775 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2764. Min Range: -9.2764
Max Act: 8.3389. Min Act: -0.1700
Data Index: 1117213 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2764. Min Range: -9.2764
Max Act: 8.4014. Min Act: -0.1700
Data Index: 8404480 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2764. Min Range: -9.2764
Max Act: 8.4014. Min Act: -0.1700
Data Index: 2367049 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2764. Min Range: -9.2764
Max Act: 8.3389. Min Act: -0.1700
Data Index: 7677323 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2764. Min Range: -9.2764
Max Act: 8.3389. Min Act: -0.1700
Data Index: 5127533 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2764. Min Range: -9.2764
Max Act: 8.3389. Min Act: -0.1700
Data Index: 2141715 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2764. Min Range: -9.2764
Max Act: 8.3389. Min Act: -0.1700
Data Index: 6480809 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2764. Min Range: -9.2764
Max Act: 8.3389. Min Act: -0.1700
Data Index: 2685899 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2764. Min Range: -9.2764
Max Act: 8.2764. Min Act: -0.1700
Data Index: 1146554 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2764. Min Range: -9.2764
Max Act: 8.2764. Min Act: -0.1700
Data Index: 2021753 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2764. Min Range: -9.2764
Max Act: 8.2764. Min Act: -0.1700
Data Index: 5134403 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2764. Min Range: -9.2764
Max Act: 8.2139. Min Act: -0.1700
Data Index: 4287392 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2764. Min Range: -9.2764
Max Act: 8.2764. Min Act: -0.1700
Data Index: 2043209 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2764. Min Range: -9.2764
Max Act: 8.1514. Min Act: -0.1700
Data Index: 5720236 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19