Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4563 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1147. Min Range: -6.1147
Max Act: 6.1147. Min Act: -0.1700
Data Index: 846918 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1147. Min Range: -6.1147
Max Act: 6.0522. Min Act: -0.1700
Data Index: 6137228 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1147. Min Range: -6.1147
Max Act: 5.8959. Min Act: -0.1700
Data Index: 847155 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1147. Min Range: -6.1147
Max Act: 5.8959. Min Act: -0.1700
Data Index: 405362 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1147. Min Range: -6.1147
Max Act: 5.8022. Min Act: -0.1700
Data Index: 7686175 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1147. Min Range: -6.1147
Max Act: 5.7709. Min Act: -0.1700
Data Index: 1050841 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1147. Min Range: -6.1147
Max Act: 5.7709. Min Act: -0.1700
Data Index: 7870082 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1147. Min Range: -6.1147
Max Act: 5.7084. Min Act: -0.1700
Data Index: 7771638 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1147. Min Range: -6.1147
Max Act: 5.6772. Min Act: -0.1700
Data Index: 4672209 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1147. Min Range: -6.1147
Max Act: 5.6772. Min Act: -0.1700
Data Index: 405369 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1147. Min Range: -6.1147
Max Act: 5.7084. Min Act: -0.1700
Data Index: 1793137 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1147. Min Range: -6.1147
Max Act: 5.6772. Min Act: -0.1700
Data Index: 4906751 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1147. Min Range: -6.1147
Max Act: 5.6459. Min Act: -0.1700
Data Index: 6644846 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1147. Min Range: -6.1147
Max Act: 5.6459. Min Act: -0.1700
Data Index: 5153213 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1147. Min Range: -6.1147
Max Act: 5.6772. Min Act: -0.1700
Data Index: 6837366 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1147. Min Range: -6.1147
Max Act: 5.6147. Min Act: -0.1700
Data Index: 3038396 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1147. Min Range: -6.1147
Max Act: 5.6459. Min Act: -0.1700
Data Index: 3038397 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1147. Min Range: -6.1147
Max Act: 5.6459. Min Act: -0.1700
Data Index: 1861061 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1147. Min Range: -6.1147
Max Act: 5.6147. Min Act: -0.1700
Data Index: 90140 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1147. Min Range: -6.1147
Max Act: 5.5834. Min Act: -0.1700
Data Index: 435369 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19