Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1380 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6813. Min Range: -2.6813
Max Act: 2.6813. Min Act: -0.1699
Data Index: 4506738 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6813. Min Range: -2.6813
Max Act: 2.6171. Min Act: -0.1698
Data Index: 6547978 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6813. Min Range: -2.6813
Max Act: 2.5849. Min Act: -0.1699
Data Index: 2543079 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6813. Min Range: -2.6813
Max Act: 2.5688. Min Act: -0.1700
Data Index: 5216417 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6813. Min Range: -2.6813
Max Act: 2.5526. Min Act: -0.1700
Data Index: 6934694 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6813. Min Range: -2.6813
Max Act: 2.5365. Min Act: -0.1699
Data Index: 3972029 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6813. Min Range: -2.6813
Max Act: 2.5203. Min Act: -0.1700
Data Index: 7220833 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6813. Min Range: -2.6813
Max Act: 2.5203. Min Act: -0.1699
Data Index: 7506716 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6813. Min Range: -2.6813
Max Act: 2.5041. Min Act: -0.1695
Data Index: 3488999 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6813. Min Range: -2.6813
Max Act: 2.5203. Min Act: -0.1700
Data Index: 7699901 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6813. Min Range: -2.6813
Max Act: 2.5041. Min Act: -0.1699
Data Index: 6948772 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6813. Min Range: -2.6813
Max Act: 2.5041. Min Act: -0.1700
Data Index: 5398860 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6813. Min Range: -2.6813
Max Act: 2.4879. Min Act: -0.1686
Data Index: 4594364 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6813. Min Range: -2.6813
Max Act: 2.5041. Min Act: -0.1699
Data Index: 442649 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6813. Min Range: -2.6813
Max Act: 2.5041. Min Act: -0.1694
Data Index: 5306329 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6813. Min Range: -2.6813
Max Act: 2.5041. Min Act: -0.1698
Data Index: 7677879 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6813. Min Range: -2.6813
Max Act: 2.4879. Min Act: -0.1694
Data Index: 2969119 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6813. Min Range: -2.6813
Max Act: 2.4879. Min Act: -0.1664
Data Index: 342507 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6813. Min Range: -2.6813
Max Act: 2.4879. Min Act: -0.1697
Data Index: 7370575 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6813. Min Range: -2.6813
Max Act: 2.4879. Min Act: -0.1700
Data Index: 5782641 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19