Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5443 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1824. Min Range: -9.1824
Max Act: 9.1824. Min Act: -0.1700
Data Index: 3219995 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1824. Min Range: -9.1824
Max Act: 9.1824. Min Act: -0.1700
Data Index: 8539464 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1824. Min Range: -9.1824
Max Act: 8.9324. Min Act: -0.1700
Data Index: 8413492 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1824. Min Range: -9.1824
Max Act: 8.8699. Min Act: -0.1700
Data Index: 36534 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1824. Min Range: -9.1824
Max Act: 8.8699. Min Act: -0.1700
Data Index: 3467428 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1824. Min Range: -9.1824
Max Act: 8.6824. Min Act: -0.1700
Data Index: 1597998 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1824. Min Range: -9.1824
Max Act: 8.6199. Min Act: -0.1700
Data Index: 8227322 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1824. Min Range: -9.1824
Max Act: 8.6199. Min Act: -0.1700
Data Index: 226401 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1824. Min Range: -9.1824
Max Act: 8.6199. Min Act: -0.1700
Data Index: 1948403 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1824. Min Range: -9.1824
Max Act: 8.6824. Min Act: -0.1700
Data Index: 364347 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1824. Min Range: -9.1824
Max Act: 8.6199. Min Act: -0.1700
Data Index: 5436392 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1824. Min Range: -9.1824
Max Act: 8.5574. Min Act: -0.1700
Data Index: 2789052 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1824. Min Range: -9.1824
Max Act: 8.5574. Min Act: -0.1700
Data Index: 5875512 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1824. Min Range: -9.1824
Max Act: 8.5574. Min Act: -0.1700
Data Index: 5657250 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1824. Min Range: -9.1824
Max Act: 8.5574. Min Act: -0.1700
Data Index: 7221789 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1824. Min Range: -9.1824
Max Act: 8.4949. Min Act: -0.1700
Data Index: 8640077 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1824. Min Range: -9.1824
Max Act: 8.4949. Min Act: -0.1700
Data Index: 1162645 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1824. Min Range: -9.1824
Max Act: 8.4949. Min Act: -0.1699
Data Index: 947505 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1824. Min Range: -9.1824
Max Act: 8.4324. Min Act: -0.1700
Data Index: 4746827 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1824. Min Range: -9.1824
Max Act: 8.4324. Min Act: -0.1700
Data Index: 3140743 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19