Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3240 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8676. Min Range: -7.8676
Max Act: 7.8676. Min Act: -0.1700
Data Index: 8399164 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8676. Min Range: -7.8676
Max Act: 7.8051. Min Act: -0.1700
Data Index: 3270639 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8676. Min Range: -7.8676
Max Act: 7.7426. Min Act: -0.1700
Data Index: 981554 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8676. Min Range: -7.8676
Max Act: 7.6801. Min Act: -0.1700
Data Index: 5391552 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8676. Min Range: -7.8676
Max Act: 7.6801. Min Act: -0.1700
Data Index: 5347545 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8676. Min Range: -7.8676
Max Act: 7.6176. Min Act: -0.1700
Data Index: 1913481 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8676. Min Range: -7.8676
Max Act: 7.5551. Min Act: -0.1700
Data Index: 340761 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8676. Min Range: -7.8676
Max Act: 7.6176. Min Act: -0.1700
Data Index: 6991716 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8676. Min Range: -7.8676
Max Act: 7.6176. Min Act: -0.1700
Data Index: 8762505 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8676. Min Range: -7.8676
Max Act: 7.6176. Min Act: -0.1700
Data Index: 2556997 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8676. Min Range: -7.8676
Max Act: 7.6176. Min Act: -0.1700
Data Index: 6496170 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8676. Min Range: -7.8676
Max Act: 7.6176. Min Act: -0.1700
Data Index: 4886311 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8676. Min Range: -7.8676
Max Act: 7.5551. Min Act: -0.1700
Data Index: 4147516 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8676. Min Range: -7.8676
Max Act: 7.6176. Min Act: -0.1700
Data Index: 1655226 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8676. Min Range: -7.8676
Max Act: 7.5239. Min Act: -0.1700
Data Index: 4755003 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8676. Min Range: -7.8676
Max Act: 7.5239. Min Act: -0.1700
Data Index: 376023 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8676. Min Range: -7.8676
Max Act: 7.4926. Min Act: -0.1700
Data Index: 7279478 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8676. Min Range: -7.8676
Max Act: 7.4614. Min Act: -0.1700
Data Index: 3581660 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8676. Min Range: -7.8676
Max Act: 7.4614. Min Act: -0.1700
Data Index: 1648110 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8676. Min Range: -7.8676
Max Act: 7.4301. Min Act: -0.1700
Data Index: 540369 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19