Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3526 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3568. Min Range: -5.3568
Max Act: 5.3568. Min Act: -0.1700
Data Index: 6588219 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3568. Min Range: -5.3568
Max Act: 5.2631. Min Act: -0.1700
Data Index: 5841241 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3568. Min Range: -5.3568
Max Act: 5.2006. Min Act: -0.1700
Data Index: 4884865 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3568. Min Range: -5.3568
Max Act: 5.2006. Min Act: -0.1700
Data Index: 7006825 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3568. Min Range: -5.3568
Max Act: 5.2006. Min Act: -0.1700
Data Index: 7009545 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3568. Min Range: -5.3568
Max Act: 5.1381. Min Act: -0.1700
Data Index: 6139228 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3568. Min Range: -5.3568
Max Act: 5.1381. Min Act: -0.1700
Data Index: 3463384 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3568. Min Range: -5.3568
Max Act: 5.1068. Min Act: -0.1700
Data Index: 2643371 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3568. Min Range: -5.3568
Max Act: 5.1693. Min Act: -0.1700
Data Index: 5412527 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3568. Min Range: -5.3568
Max Act: 5.1381. Min Act: -0.1700
Data Index: 4179962 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3568. Min Range: -5.3568
Max Act: 5.1068. Min Act: -0.1700
Data Index: 7991112 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3568. Min Range: -5.3568
Max Act: 5.1068. Min Act: -0.1700
Data Index: 7867733 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3568. Min Range: -5.3568
Max Act: 5.1068. Min Act: -0.1700
Data Index: 7066002 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3568. Min Range: -5.3568
Max Act: 5.1068. Min Act: -0.1700
Data Index: 2786016 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3568. Min Range: -5.3568
Max Act: 5.1068. Min Act: -0.1700
Data Index: 2014269 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3568. Min Range: -5.3568
Max Act: 5.1068. Min Act: -0.1700
Data Index: 6425027 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3568. Min Range: -5.3568
Max Act: 5.0756. Min Act: -0.1700
Data Index: 2347016 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3568. Min Range: -5.3568
Max Act: 5.0756. Min Act: -0.1700
Data Index: 4980039 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3568. Min Range: -5.3568
Max Act: 5.0131. Min Act: -0.1700
Data Index: 323806 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3568. Min Range: -5.3568
Max Act: 5.0443. Min Act: -0.1700
Data Index: 5708118 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19