Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2770 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.2044. Min Range: -1.2044
Max Act: 1.1868. Min Act: -0.1700
Data Index: 8781369 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2044. Min Range: -1.2044
Max Act: 1.2044. Min Act: -0.1700
Data Index: 6872958 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2044. Min Range: -1.2044
Max Act: 1.1516. Min Act: -0.1700
Data Index: 387901 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2044. Min Range: -1.2044
Max Act: 1.1341. Min Act: -0.1700
Data Index: 4324767 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2044. Min Range: -1.2044
Max Act: 1.1341. Min Act: -0.1697
Data Index: 1360607 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2044. Min Range: -1.2044
Max Act: 1.0990. Min Act: -0.1700
Data Index: 2235847 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2044. Min Range: -1.2044
Max Act: 1.0990. Min Act: -0.1699
Data Index: 2169114 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2044. Min Range: -1.2044
Max Act: 1.0640. Min Act: -0.1698
Data Index: 7551283 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2044. Min Range: -1.2044
Max Act: 1.0640. Min Act: -0.1699
Data Index: 1578499 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2044. Min Range: -1.2044
Max Act: 1.0465. Min Act: -0.1700
Data Index: 6863712 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2044. Min Range: -1.2044
Max Act: 1.0465. Min Act: -0.1700
Data Index: 2486918 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2044. Min Range: -1.2044
Max Act: 1.0465. Min Act: -0.1699
Data Index: 7160298 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2044. Min Range: -1.2044
Max Act: 1.0465. Min Act: -0.1700
Data Index: 4213078 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2044. Min Range: -1.2044
Max Act: 1.0291. Min Act: -0.1696
Data Index: 6903772 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2044. Min Range: -1.2044
Max Act: 1.0291. Min Act: -0.1700
Data Index: 6552387 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2044. Min Range: -1.2044
Max Act: 1.0291. Min Act: -0.1700
Data Index: 5016103 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2044. Min Range: -1.2044
Max Act: 1.0117. Min Act: -0.1700
Data Index: 6655663 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2044. Min Range: -1.2044
Max Act: 1.0117. Min Act: -0.1700
Data Index: 5769202 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2044. Min Range: -1.2044
Max Act: 1.0291. Min Act: -0.1700
Data Index: 6288680 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2044. Min Range: -1.2044
Max Act: 1.0117. Min Act: -0.1698
Data Index: 708208 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19