Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3969 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3741. Min Range: -6.3741
Max Act: 6.3741. Min Act: -0.1700
Data Index: 8206264 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3741. Min Range: -6.3741
Max Act: 6.2491. Min Act: -0.1700
Data Index: 118808 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3741. Min Range: -6.3741
Max Act: 6.1554. Min Act: -0.1700
Data Index: 4672044 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3741. Min Range: -6.3741
Max Act: 6.0304. Min Act: -0.1700
Data Index: 906317 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3741. Min Range: -6.3741
Max Act: 6.0616. Min Act: -0.1700
Data Index: 2156988 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3741. Min Range: -6.3741
Max Act: 6.0304. Min Act: -0.1700
Data Index: 678035 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3741. Min Range: -6.3741
Max Act: 5.9679. Min Act: -0.1700
Data Index: 8263246 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3741. Min Range: -6.3741
Max Act: 5.9366. Min Act: -0.1700
Data Index: 5027563 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3741. Min Range: -6.3741
Max Act: 5.9054. Min Act: -0.1700
Data Index: 8755543 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3741. Min Range: -6.3741
Max Act: 5.8741. Min Act: -0.1700
Data Index: 5714005 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3741. Min Range: -6.3741
Max Act: 5.8429. Min Act: -0.1700
Data Index: 1092837 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3741. Min Range: -6.3741
Max Act: 5.7804. Min Act: -0.1700
Data Index: 328269 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3741. Min Range: -6.3741
Max Act: 5.8429. Min Act: -0.1700
Data Index: 3621067 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3741. Min Range: -6.3741
Max Act: 5.8116. Min Act: -0.1700
Data Index: 4890514 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3741. Min Range: -6.3741
Max Act: 5.7804. Min Act: -0.1700
Data Index: 557679 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3741. Min Range: -6.3741
Max Act: 5.7804. Min Act: -0.1700
Data Index: 1321961 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3741. Min Range: -6.3741
Max Act: 5.7804. Min Act: -0.1700
Data Index: 5447295 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3741. Min Range: -6.3741
Max Act: 5.7804. Min Act: -0.1700
Data Index: 5618628 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3741. Min Range: -6.3741
Max Act: 5.7491. Min Act: -0.1700
Data Index: 5201315 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3741. Min Range: -6.3741
Max Act: 5.7179. Min Act: -0.1700
Data Index: 1993379 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19