Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3559 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2504. Min Range: -6.2504
Max Act: 6.2504. Min Act: -0.1700
Data Index: 557876 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2504. Min Range: -6.2504
Max Act: 6.1254. Min Act: -0.1700
Data Index: 444746 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2504. Min Range: -6.2504
Max Act: 6.1254. Min Act: -0.1700
Data Index: 8567448 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2504. Min Range: -6.2504
Max Act: 6.0629. Min Act: -0.1700
Data Index: 5174467 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2504. Min Range: -6.2504
Max Act: 6.0316. Min Act: -0.1700
Data Index: 8819383 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2504. Min Range: -6.2504
Max Act: 6.0629. Min Act: -0.1700
Data Index: 529299 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2504. Min Range: -6.2504
Max Act: 5.9691. Min Act: -0.1700
Data Index: 4654482 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2504. Min Range: -6.2504
Max Act: 5.9691. Min Act: -0.1700
Data Index: 4482064 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2504. Min Range: -6.2504
Max Act: 5.9691. Min Act: -0.1700
Data Index: 2798962 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2504. Min Range: -6.2504
Max Act: 5.9379. Min Act: -0.1700
Data Index: 6112621 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2504. Min Range: -6.2504
Max Act: 5.9379. Min Act: -0.1700
Data Index: 4007013 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2504. Min Range: -6.2504
Max Act: 5.9379. Min Act: -0.1700
Data Index: 808004 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2504. Min Range: -6.2504
Max Act: 5.9379. Min Act: -0.1700
Data Index: 8449592 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2504. Min Range: -6.2504
Max Act: 5.9379. Min Act: -0.1700
Data Index: 6345944 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2504. Min Range: -6.2504
Max Act: 5.9379. Min Act: -0.1700
Data Index: 120269 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2504. Min Range: -6.2504
Max Act: 5.9066. Min Act: -0.1700
Data Index: 2613921 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2504. Min Range: -6.2504
Max Act: 5.9066. Min Act: -0.1700
Data Index: 808003 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2504. Min Range: -6.2504
Max Act: 5.9066. Min Act: -0.1700
Data Index: 2707900 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2504. Min Range: -6.2504
Max Act: 5.9066. Min Act: -0.1700
Data Index: 2053826 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2504. Min Range: -6.2504
Max Act: 5.9066. Min Act: -0.1700
Data Index: 2750287 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19