Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4903 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.9324. Min Range: -8.9324
Max Act: 8.9324. Min Act: -0.1700
Data Index: 1496660 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9324. Min Range: -8.9324
Max Act: 8.8699. Min Act: -0.1700
Data Index: 6236075 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9324. Min Range: -8.9324
Max Act: 8.8074. Min Act: -0.1700
Data Index: 1909290 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9324. Min Range: -8.9324
Max Act: 8.6824. Min Act: -0.1700
Data Index: 7269359 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9324. Min Range: -8.9324
Max Act: 8.6199. Min Act: -0.1700
Data Index: 6096723 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9324. Min Range: -8.9324
Max Act: 8.5574. Min Act: -0.1700
Data Index: 439062 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9324. Min Range: -8.9324
Max Act: 8.4324. Min Act: -0.1700
Data Index: 5493568 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9324. Min Range: -8.9324
Max Act: 8.4949. Min Act: -0.1700
Data Index: 2066220 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9324. Min Range: -8.9324
Max Act: 8.4324. Min Act: -0.1700
Data Index: 35862 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9324. Min Range: -8.9324
Max Act: 8.3699. Min Act: -0.1700
Data Index: 2163767 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9324. Min Range: -8.9324
Max Act: 8.3074. Min Act: -0.1700
Data Index: 2497791 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9324. Min Range: -8.9324
Max Act: 8.3074. Min Act: -0.1700
Data Index: 630750 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9324. Min Range: -8.9324
Max Act: 8.2449. Min Act: -0.1700
Data Index: 2050998 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9324. Min Range: -8.9324
Max Act: 8.2449. Min Act: -0.1700
Data Index: 2359040 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9324. Min Range: -8.9324
Max Act: 8.2449. Min Act: -0.1700
Data Index: 5902337 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9324. Min Range: -8.9324
Max Act: 8.2449. Min Act: -0.1700
Data Index: 2484007 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9324. Min Range: -8.9324
Max Act: 8.1824. Min Act: -0.1700
Data Index: 4712909 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9324. Min Range: -8.9324
Max Act: 8.1824. Min Act: -0.1700
Data Index: 4560526 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9324. Min Range: -8.9324
Max Act: 8.1824. Min Act: -0.1700
Data Index: 2052080 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9324. Min Range: -8.9324
Max Act: 8.1824. Min Act: -0.1700
Data Index: 2020357 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19