Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 549 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0228. Min Range: -5.0228
Max Act: 5.0228. Min Act: -0.1700
Data Index: 7310600 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0228. Min Range: -5.0228
Max Act: 5.0228. Min Act: -0.1700
Data Index: 5227246 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0228. Min Range: -5.0228
Max Act: 4.9915. Min Act: -0.1700
Data Index: 895176 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0228. Min Range: -5.0228
Max Act: 4.8978. Min Act: -0.1700
Data Index: 7502662 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0228. Min Range: -5.0228
Max Act: 4.8353. Min Act: -0.1700
Data Index: 2394209 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0228. Min Range: -5.0228
Max Act: 4.8040. Min Act: -0.1700
Data Index: 3719610 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0228. Min Range: -5.0228
Max Act: 4.7728. Min Act: -0.1700
Data Index: 1510733 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0228. Min Range: -5.0228
Max Act: 4.8040. Min Act: -0.1700
Data Index: 7805158 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0228. Min Range: -5.0228
Max Act: 4.7728. Min Act: -0.1700
Data Index: 3912913 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0228. Min Range: -5.0228
Max Act: 4.7728. Min Act: -0.1700
Data Index: 257895 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0228. Min Range: -5.0228
Max Act: 4.7728. Min Act: -0.1700
Data Index: 5784397 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0228. Min Range: -5.0228
Max Act: 4.7415. Min Act: -0.1700
Data Index: 7080702 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0228. Min Range: -5.0228
Max Act: 4.7415. Min Act: -0.1700
Data Index: 1845786 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0228. Min Range: -5.0228
Max Act: 4.7103. Min Act: -0.1700
Data Index: 7831255 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0228. Min Range: -5.0228
Max Act: 4.7103. Min Act: -0.1700
Data Index: 3539686 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0228. Min Range: -5.0228
Max Act: 4.6790. Min Act: -0.1700
Data Index: 224860 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0228. Min Range: -5.0228
Max Act: 4.6790. Min Act: -0.1700
Data Index: 330328 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0228. Min Range: -5.0228
Max Act: 4.6478. Min Act: -0.1700
Data Index: 655427 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0228. Min Range: -5.0228
Max Act: 4.6478. Min Act: -0.1700
Data Index: 6794889 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0228. Min Range: -5.0228
Max Act: 4.6478. Min Act: -0.1700
Data Index: 4203720 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19