Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1188 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7449. Min Range: -9.7449
Max Act: 9.7449. Min Act: -0.1700
Data Index: 3415031 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7449. Min Range: -9.7449
Max Act: 9.1824. Min Act: -0.1700
Data Index: 5596901 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7449. Min Range: -9.7449
Max Act: 9.1824. Min Act: -0.1700
Data Index: 5352557 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7449. Min Range: -9.7449
Max Act: 9.1824. Min Act: -0.1700
Data Index: 6435367 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7449. Min Range: -9.7449
Max Act: 9.1824. Min Act: -0.1700
Data Index: 4877262 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7449. Min Range: -9.7449
Max Act: 9.1199. Min Act: -0.1700
Data Index: 1896284 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7449. Min Range: -9.7449
Max Act: 9.1824. Min Act: -0.1700
Data Index: 5099362 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7449. Min Range: -9.7449
Max Act: 8.8699. Min Act: -0.1700
Data Index: 4949130 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7449. Min Range: -9.7449
Max Act: 8.8699. Min Act: -0.1700
Data Index: 7337187 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7449. Min Range: -9.7449
Max Act: 8.8699. Min Act: -0.1700
Data Index: 2695663 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7449. Min Range: -9.7449
Max Act: 8.8074. Min Act: -0.1700
Data Index: 7278461 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7449. Min Range: -9.7449
Max Act: 8.8074. Min Act: -0.1700
Data Index: 6619333 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7449. Min Range: -9.7449
Max Act: 8.8074. Min Act: -0.1700
Data Index: 4706902 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7449. Min Range: -9.7449
Max Act: 8.7449. Min Act: -0.1700
Data Index: 8691542 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7449. Min Range: -9.7449
Max Act: 8.7449. Min Act: -0.1700
Data Index: 1525564 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7449. Min Range: -9.7449
Max Act: 8.7449. Min Act: -0.1700
Data Index: 997379 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7449. Min Range: -9.7449
Max Act: 8.6824. Min Act: -0.1700
Data Index: 63707 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7449. Min Range: -9.7449
Max Act: 8.6824. Min Act: -0.1700
Data Index: 1842024 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7449. Min Range: -9.7449
Max Act: 8.6824. Min Act: -0.1700
Data Index: 4723841 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7449. Min Range: -9.7449
Max Act: 8.6824. Min Act: -0.1700
Data Index: 2467967 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19